# Chock.sh

> Blocks your coding agent's wrong moves before they land.

Chock turns a picked set of guardrail policies into plugins for AI agents. The coding section holds 71 policies, each labelled blocks, asks, warns or advisory, on a catalog pinned at 1e60d211c1bb. Ask the user before picking or installing anything.

## Docs

- [Site home](/index.md): what chock is and who it is for
- [Security](/security/index.md): what chock is and is not
- [FAQ](/faq/index.md): common questions
- [For AI agents](/for-agents/index.md): how to read this site and its data
- [Report an issue](/report/index.md): where each kind of problem is reported

- [Docs: Overview](/docs/index.md): How chock works and how to use it: plugins for your agent, or hooks in your repo.
- [Docs: Quickstart: plugin](/docs/quickstart/plugin/index.md): Install the engine, pick policies, and build one plugin for your agent.
- [Docs: Quickstart: repo](/docs/quickstart/repo/index.md): Onboard a git repository with chock init and chock sync: agent hooks, git hooks and CI.
- [Docs: Agents](/docs/agents/index.md): Every agent agentseam records: how chock installs on it, what it can enforce, and what that rests on.
- [Docs: Policies](/docs/policies/index.md): Every catalog policy: what it does, its grade on each agent, what it misses, and an example.
- [Docs: Configure](/docs/configure/index.md): Selection files, switching plugin members on and off, local policies, and where to customise.
- [Docs: Monitor](/docs/monitor/index.md): Where chock hooks log their decisions for each install method, how to read and sum up the log, and how to export it as evidence.
- [Docs: Troubleshooting](/docs/troubleshooting/index.md): Measured problems and fixes, checking hooks with chock doctor, reading the decision log, install notes per agent, what happens when a guard cannot decide, and arming a fresh clone.
- [Docs: What Chock doesn't stop](/docs/bypasses/index.md): Every known way an action gets past chock, in one place, each with the chock file that says so.
- [Docs: CLI reference](/docs/cli/index.md): Every chock command and its options, generated from the engine's own --help.
- [Docs: Release notes](/docs/release-notes/index.md): The newest versions in the engine's changelog, each linked to its entry at the pinned commit.
- [Docs: Where Chock sits](/docs/where-chock-sits/index.md): Chock beside agent identity, OS containment, gateways, inventory and browser controls: what each layer catches that Chock can't, and what Chock catches that it can't.
- [Docs: How it works](/docs/how-it-works/index.md): The lifecycle of a policy in a repository, from authoring to a verdict and a log line, with diagrams that cite the engine's files.
- [Docs: Where policies run](/docs/how-it-works/surfaces/index.md): Where a compiled policy runs: each hook point as chock's docs describe it, the engine emitter that writes it, and the agents that have it.
- [Docs: Stop and resume](/docs/how-it-works/stop/index.md): How a person stops agents in one repository or on the whole machine with chock stop, chock resume and --everywhere, what reads the stop, and its limits.
- [Docs: Architecture](/docs/architecture/index.md): How the chock repositories fit together, and the path one policy takes from the catalog to your agent's hook.
- [Docs: What agentseam is](/docs/agentseam/index.md): Agentseam, the library under chock: one handler API over each coding agent's own hooks.
- [Docs: Use it without chock](/docs/agentseam/direct/index.md): Install agentseam, write a handler, wire it into your agents' hooks and see it refuse, from a recorded run.
- [Docs: Python API](/docs/agentseam/api/index.md): Every name agentseam exports, with its signature and docstring, read from the pinned release.
- [Docs: Agentseam CLI](/docs/agentseam/cli/index.md): The agentseam command and every subcommand, generated from its argument parser.
- [Docs: Adopt catalog policies](/docs/catalog/adopt/index.md): Install policies from chock-catalog into your repository, pinned to a commit and checked against a hash, with the output of a real run.
- [Docs: Add a policy to the catalog](/docs/catalog/contribute/index.md): Add a new policy to chock-catalog step by step: folder, manifest, implementation, evals, the generators, and the CI jobs a pull request runs.
- [Docs: Your own policy](/docs/write/own-policy/index.md): Create a policy in your own repository step by step: scaffold it, read its manifest and evals, validate, eval, sync, and see a commit refused. Every output is from a recorded run.
- [Docs: On the fly](/docs/write/on-the-fly/index.md): Make a policy while you work: ask your agent to run the policy-init skill, scaffold one with a single chock new, or fill the templates in the browser. A recorded run writes a guard and feeds it an agent's hook event.
- [Docs: Manifest reference](/docs/write/manifest/index.md): Every field of a policy's manifest.yaml, with its type, whether it is required and the values it allows, read from the engine's schema at the pinned commit.
- [Docs: Evals reference](/docs/write/evals/index.md): How a policy's evals/suite.yaml is laid out, what each case says, and every field of the engine's eval schema at the pinned commit.
- [Docs: Aider](/docs/agents/aider/index.md): Aider and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Amp](/docs/agents/amp/index.md): Amp and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Antigravity](/docs/agents/antigravity/index.md): Antigravity and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Claude Code](/docs/agents/claude-code/index.md): Claude Code and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Cline](/docs/agents/cline/index.md): Cline and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: OpenAI Codex CLI](/docs/agents/codex-cli/index.md): OpenAI Codex CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: GitHub Copilot (Agent Plugins 1.0 marketplace bundle)](/docs/agents/copilot/index.md): GitHub Copilot (Agent Plugins 1.0 marketplace bundle) and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Cursor](/docs/agents/cursor/index.md): Cursor and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: DeepSeek Harness (dsh)](/docs/agents/deepseek-harness/index.md): DeepSeek Harness (dsh) and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Devin](/docs/agents/devin/index.md): Devin and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Factory Droid](/docs/agents/factory-droid/index.md): Factory Droid and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Gemini CLI](/docs/agents/gemini-cli/index.md): Gemini CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: goose](/docs/agents/goose/index.md): goose and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Grok CLI](/docs/agents/grok/index.md): Grok CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Junie CLI](/docs/agents/junie/index.md): Junie CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Kilo Code](/docs/agents/kilo-code/index.md): Kilo Code and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Kimi Code CLI](/docs/agents/kimi-code/index.md): Kimi Code CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Kiro](/docs/agents/kiro/index.md): Kiro and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Mistral Vibe](/docs/agents/mistral-vibe/index.md): Mistral Vibe and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: OpenCode](/docs/agents/opencode/index.md): OpenCode and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: OpenHands](/docs/agents/openhands/index.md): OpenHands and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Replit Agent](/docs/agents/replit/index.md): Replit Agent and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Roo Code](/docs/agents/roo-code/index.md): Roo Code and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Tabnine CLI](/docs/agents/tabnine/index.md): Tabnine CLI and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: GitHub Copilot (VS Code agent mode / CLI)](/docs/agents/vscode-copilot/index.md): GitHub Copilot (VS Code agent mode / CLI) and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Windsurf (Cascade)](/docs/agents/windsurf/index.md): Windsurf (Cascade) and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Zed](/docs/agents/zed/index.md): Zed and chock: install methods and steps, what it can enforce, and the evidence behind it.
- [Docs: Agent Discipline](/docs/policies/agent-discipline/index.md): Agent Discipline: what it does, its label on each agent, what it misses, and examples.
- [Docs: Agentic Code Security](/docs/policies/agentic-code-security/index.md): Agentic Code Security: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Agents Started With Safety Off](/docs/policies/block-unguarded-agent-spawn/index.md): Block Agents Started With Safety Off: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Curl Piped to Shell](/docs/policies/block-curl-pipe-sh/index.md): Block Curl Piped to Shell: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Destructive Commands](/docs/policies/block-destructive-commands/index.md): Block Destructive Commands: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Files That Skip Git Hooks](/docs/policies/block-hook-bypass-in-files/index.md): Block Files That Skip Git Hooks: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Invisible Unicode](/docs/policies/block-invisible-unicode/index.md): Block Invisible Unicode: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Known-Malicious Packages](/docs/policies/compromised-package-ioc/index.md): Block Known-Malicious Packages: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Persistence and Publishing Commands](/docs/policies/block-persistence-shapes/index.md): Block Persistence and Publishing Commands: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Reading Stored Credentials](/docs/policies/block-secret-store-reads/index.md): Block Reading Stored Credentials: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Risky Characters in File and Branch Names](/docs/policies/refname-filename-metachar/index.md): Block Risky Characters in File and Branch Names: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Skipping Git Hooks](/docs/policies/block-no-verify/index.md): Block Skipping Git Hooks: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Test Skips](/docs/policies/block-test-skips/index.md): Block Test Skips: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Unapproved Egress](/docs/policies/block-unapproved-egress/index.md): Block Unapproved Egress: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Unpinned Agent Components](/docs/policies/block-unpinned-agent-components/index.md): Block Unpinned Agent Components: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Unsafe Code Execution](/docs/policies/block-unsafe-code-execution/index.md): Block Unsafe Code Execution: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Unsafe Package Registry Settings](/docs/policies/registry-config/index.md): Block Unsafe Package Registry Settings: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Weakened Build Hardening](/docs/policies/hardening-flags/index.md): Block Weakened Build Hardening: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Wildcard Agent Permissions](/docs/policies/block-wildcard-agent-permissions/index.md): Block Wildcard Agent Permissions: what it does, its label on each agent, what it misses, and examples.
- [Docs: Block Wildcard IAM Grants](/docs/policies/block-wildcard-iam/index.md): Block Wildcard IAM Grants: what it does, its label on each agent, what it misses, and examples.
- [Docs: CI GitHub Actions Security](/docs/policies/ci-github-actions-security/index.md): CI GitHub Actions Security: what it does, its label on each agent, what it misses, and examples.
- [Docs: Code Safety](/docs/policies/code-safety/index.md): Code Safety: what it does, its label on each agent, what it misses, and examples.
- [Docs: Context Hygiene](/docs/policies/context-hygiene/index.md): Context Hygiene: what it does, its label on each agent, what it misses, and examples.
- [Docs: Dependency Allowlist](/docs/policies/verify-dependency-exists/index.md): Dependency Allowlist: what it does, its label on each agent, what it misses, and examples.
- [Docs: Dockerfile and Compose Security](/docs/policies/dockerfile-compose-security/index.md): Dockerfile and Compose Security: what it does, its label on each agent, what it misses, and examples.
- [Docs: EU AI Act — High-Risk Triage](/docs/policies/eu-ai-act-high-risk-triage/index.md): EU AI Act — High-Risk Triage: what it does, its label on each agent, what it misses, and examples.
- [Docs: EU AI Act — Prohibited Practices](/docs/policies/eu-ai-act-prohibited-practices/index.md): EU AI Act — Prohibited Practices: what it does, its label on each agent, what it misses, and examples.
- [Docs: EU AI Act — Transparency](/docs/policies/eu-ai-act-transparency/index.md): EU AI Act — Transparency: what it does, its label on each agent, what it misses, and examples.
- [Docs: Flag Dev Tools That Run Code on Open](/docs/policies/agent-devenv-autoexec/index.md): Flag Dev Tools That Run Code on Open: what it does, its label on each agent, what it misses, and examples.
- [Docs: Flag Downloads Run as Code in Files](/docs/policies/block-fetch-exec-in-files/index.md): Flag Downloads Run as Code in Files: what it does, its label on each agent, what it misses, and examples.
- [Docs: Flag Hidden Binary Files in Tests](/docs/policies/opaque-blob-guard/index.md): Flag Hidden Binary Files in Tests: what it does, its label on each agent, what it misses, and examples.
- [Docs: Git Safety](/docs/policies/git-safety/index.md): Git Safety: what it does, its label on each agent, what it misses, and examples.
- [Docs: Guard Deletion and Mitigation Removal](/docs/policies/guard-deletion/index.md): Guard Deletion and Mitigation Removal: what it does, its label on each agent, what it misses, and examples.
- [Docs: Guard Memory Writes](/docs/policies/guard-memory-writes/index.md): Guard Memory Writes: what it does, its label on each agent, what it misses, and examples.
- [Docs: IAM Policy Scan](/docs/policies/iam-policy-scan/index.md): IAM Policy Scan: what it does, its label on each agent, what it misses, and examples.
- [Docs: Injection Defense](/docs/policies/injection-defense/index.md): Injection Defense: what it does, its label on each agent, what it misses, and examples.
- [Docs: Java Security Rules](/docs/policies/java-security/index.md): Java Security Rules: what it does, its label on each agent, what it misses, and examples.
- [Docs: Keep Accessibility From Regressing](/docs/policies/no-a11y-regression/index.md): Keep Accessibility From Regressing: what it does, its label on each agent, what it misses, and examples.
- [Docs: Keep Changes Small Enough to Review](/docs/policies/limit-diff-size/index.md): Keep Changes Small Enough to Review: what it does, its label on each agent, what it misses, and examples.
- [Docs: Lockfile Integrity](/docs/policies/lockfile-integrity/index.md): Lockfile Integrity: what it does, its label on each agent, what it misses, and examples.
- [Docs: Match the Owner's Coding Style](/docs/policies/chock-mise/index.md): Match the Owner's Coding Style: what it does, its label on each agent, what it misses, and examples.
- [Docs: Memory Discipline](/docs/policies/memory-discipline/index.md): Memory Discipline: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI01 — Agent Goal Hijack](/docs/policies/owasp-asi01-agent-goal-hijack/index.md): OWASP ASI01 — Agent Goal Hijack: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI02 — Tool Misuse & Exploitation](/docs/policies/owasp-asi02-tool-misuse/index.md): OWASP ASI02 — Tool Misuse & Exploitation: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI03 — Identity & Privilege Abuse](/docs/policies/owasp-asi03-identity-privilege-abuse/index.md): OWASP ASI03 — Identity & Privilege Abuse: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI04 — Agentic Supply Chain Vulnerabilities](/docs/policies/owasp-asi04-agentic-supply-chain/index.md): OWASP ASI04 — Agentic Supply Chain Vulnerabilities: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI05 — Unexpected Code Execution](/docs/policies/owasp-asi05-unexpected-code-execution/index.md): OWASP ASI05 — Unexpected Code Execution: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI06 — Memory & Context Poisoning](/docs/policies/owasp-asi06-memory-context-poisoning/index.md): OWASP ASI06 — Memory & Context Poisoning: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI07 — Insecure Inter-Agent Communication](/docs/policies/owasp-asi07-insecure-inter-agent-communication/index.md): OWASP ASI07 — Insecure Inter-Agent Communication: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI08 — Cascading Failures](/docs/policies/owasp-asi08-cascading-failures/index.md): OWASP ASI08 — Cascading Failures: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI09 — Human-Agent Trust Exploitation](/docs/policies/owasp-asi09-human-agent-trust/index.md): OWASP ASI09 — Human-Agent Trust Exploitation: what it does, its label on each agent, what it misses, and examples.
- [Docs: OWASP ASI10 — Rogue Agents](/docs/policies/owasp-asi10-rogue-agents/index.md): OWASP ASI10 — Rogue Agents: what it does, its label on each agent, what it misses, and examples.
- [Docs: Pin GitHub Actions](/docs/policies/pin-github-actions/index.md): Pin GitHub Actions: what it does, its label on each agent, what it misses, and examples.
- [Docs: Protect Agent Config](/docs/policies/protect-agent-config/index.md): Protect Agent Config: what it does, its label on each agent, what it misses, and examples.
- [Docs: Protect CI Workflows](/docs/policies/protect-ci-workflows/index.md): Protect CI Workflows: what it does, its label on each agent, what it misses, and examples.
- [Docs: Protect Commit Privacy](/docs/policies/protect-commit-privacy/index.md): Protect Commit Privacy: what it does, its label on each agent, what it misses, and examples.
- [Docs: Protect Main Branch](/docs/policies/protect-main-branch/index.md): Protect Main Branch: what it does, its label on each agent, what it misses, and examples.
- [Docs: Protect Test Integrity](/docs/policies/protect-test-integrity/index.md): Protect Test Integrity: what it does, its label on each agent, what it misses, and examples.
- [Docs: Review Added Scanner Suppressions](/docs/policies/scan-suppression-markers/index.md): Review Added Scanner Suppressions: what it does, its label on each agent, what it misses, and examples.
- [Docs: Review Cloud Identity Switches](/docs/policies/ask-credential-switching/index.md): Review Cloud Identity Switches: what it does, its label on each agent, what it misses, and examples.
- [Docs: Review Like a Red Team](/docs/policies/review-like-a-red-team/index.md): Review Like a Red Team: what it does, its label on each agent, what it misses, and examples.
- [Docs: Review Scripts That Run on Install](/docs/policies/package-lifecycle-scripts/index.md): Review Scripts That Run on Install: what it does, its label on each agent, what it misses, and examples.
- [Docs: Review Values That Look Like Secrets](/docs/policies/scan-secrets-entropy/index.md): Review Values That Look Like Secrets: what it does, its label on each agent, what it misses, and examples.
- [Docs: Scan Agent Permission Settings](/docs/policies/agent-permissions-scan/index.md): Scan Agent Permission Settings: what it does, its label on each agent, what it misses, and examples.
- [Docs: Scan Hidden Content](/docs/policies/scan-hidden-content/index.md): Scan Hidden Content: what it does, its label on each agent, what it misses, and examples.
- [Docs: Scan Instruction Files](/docs/policies/scan-instruction-files/index.md): Scan Instruction Files: what it does, its label on each agent, what it misses, and examples.
- [Docs: Scan Secret Files](/docs/policies/scan-secret-files/index.md): Scan Secret Files: what it does, its label on each agent, what it misses, and examples.
- [Docs: Scan Secrets](/docs/policies/scan-secrets/index.md): Scan Secrets: what it does, its label on each agent, what it misses, and examples.
- [Docs: Token Efficiency](/docs/policies/token-efficiency/index.md): Token Efficiency: what it does, its label on each agent, what it misses, and examples.
- [Docs: Use Firecrawl Only as a Fallback](/docs/policies/firecrawl-fallback-only/index.md): Use Firecrawl Only as a Fallback: what it does, its label on each agent, what it misses, and examples.
- [Docs: Verify MCP Allowlist](/docs/policies/verify-mcp-allowlist/index.md): Verify MCP Allowlist: what it does, its label on each agent, what it misses, and examples.
- [Docs: chock init](/docs/cli/init/index.md): Ask the user before running chock init: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock add](/docs/cli/add/index.md): Ask the user before running chock add: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock install](/docs/cli/install/index.md): Ask the user before running chock install: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock remove](/docs/cli/remove/index.md): Ask the user before running chock remove: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock sync](/docs/cli/sync/index.md): Ask the user before running chock sync: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock check](/docs/cli/check/index.md): Ask the user before running chock check: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock status](/docs/cli/status/index.md): Ask the user before running chock status: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock stop](/docs/cli/stop/index.md): Ask the user before running chock stop: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock resume](/docs/cli/resume/index.md): Ask the user before running chock resume: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock doctor](/docs/cli/doctor/index.md): Ask the user before running chock doctor: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock incident](/docs/cli/incident/index.md): Ask the user before running chock incident: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock witness](/docs/cli/witness/index.md): Ask the user before running chock witness: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock witness export](/docs/cli/witness/export/index.md): Ask the user before running chock witness export: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock enable](/docs/cli/enable/index.md): Ask the user before running chock enable: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock disable](/docs/cli/disable/index.md): Ask the user before running chock disable: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock bundle](/docs/cli/bundle/index.md): Ask the user before running chock bundle: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock bundle on](/docs/cli/bundle/on/index.md): Ask the user before running chock bundle on: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock bundle off](/docs/cli/bundle/off/index.md): Ask the user before running chock bundle off: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock bundle status](/docs/cli/bundle/status/index.md): Ask the user before running chock bundle status: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock new](/docs/cli/new/index.md): Ask the user before running chock new: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock compile](/docs/cli/compile/index.md): Ask the user before running chock compile: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock install-skills](/docs/cli/install-skills/index.md): Ask the user before running chock install-skills: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry](/docs/cli/registry/index.md): Ask the user before running chock registry: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry init](/docs/cli/registry/init/index.md): Ask the user before running chock registry init: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry scan](/docs/cli/registry/scan/index.md): Ask the user before running chock registry scan: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry list](/docs/cli/registry/list/index.md): Ask the user before running chock registry list: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry get](/docs/cli/registry/get/index.md): Ask the user before running chock registry get: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock registry resolve](/docs/cli/registry/resolve/index.md): Ask the user before running chock registry resolve: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock plugin](/docs/cli/plugin/index.md): Ask the user before running chock plugin: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock marketplace](/docs/cli/marketplace/index.md): Ask the user before running chock marketplace: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock gateway](/docs/cli/gateway/index.md): Ask the user before running chock gateway: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock gateway run](/docs/cli/gateway/run/index.md): Ask the user before running chock gateway run: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock mcp](/docs/cli/mcp/index.md): Ask the user before running chock mcp: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock review](/docs/cli/review/index.md): Ask the user before running chock review: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock review emit](/docs/cli/review/emit/index.md): Ask the user before running chock review emit: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock review verify](/docs/cli/review/verify/index.md): Ask the user before running chock review verify: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock review require](/docs/cli/review/require/index.md): Ask the user before running chock review require: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock compliance](/docs/cli/compliance/index.md): Ask the user before running chock compliance: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock validate](/docs/cli/validate/index.md): Ask the user before running chock validate: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock verify](/docs/cli/verify/index.md): Ask the user before running chock verify: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock verify init](/docs/cli/verify/init/index.md): Ask the user before running chock verify init: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock verify verify](/docs/cli/verify/verify/index.md): Ask the user before running chock verify verify: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock eval](/docs/cli/eval/index.md): Ask the user before running chock eval: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock check-matrix](/docs/cli/check-matrix/index.md): Ask the user before running chock check-matrix: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock recompile](/docs/cli/recompile/index.md): Ask the user before running chock recompile: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock refresh](/docs/cli/refresh/index.md): Ask the user before running chock refresh: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock install-hooks](/docs/cli/install-hooks/index.md): Ask the user before running chock install-hooks: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock install-ci](/docs/cli/install-ci/index.md): Ask the user before running chock install-ci: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock policies](/docs/cli/policies/index.md): Ask the user before running chock policies: what it takes and prints, from the engine at the pinned commit.
- [Docs: chock gate-log](/docs/cli/gate-log/index.md): Ask the user before running chock gate-log: what it takes and prints, from the engine at the pinned commit.
- [Docs: The whole train](/docs/architecture/whole-train/index.md): Every repository in the chock train and how a policy travels from chock-catalog through chock to the hook your agent's client runs.
- [Docs: The life of a policy](/docs/architecture/life-of-a-policy/index.md): One policy from its manifest in chock-catalog, through chock compile and an install, to a tool call, its verdict and the decision log.
- [Docs: Lifecycle in a repository](/docs/architecture/lifecycle/index.md): The repo path from end to end. You author a policy, check it and sync it into hook files. Then each tool call, commit, push and CI run goes through the hook to a verdict and one log line.
- [Docs: Emitters and hook points](/docs/architecture/enforcement-surfaces/index.md): Which emitter of chock compile writes each hook point, and the file chock sync installs for it.
- [Docs: Stop and resume](/docs/architecture/stop-and-resume/index.md): A person's stop on agents. It shows the files chock stop and chock stop --everywhere write, the hooks that read them, and the log lines a stop leaves.

## Coding agents

- [Coding agents home](/coding/index.md): Rules for agents that write code: refuse git commit --no-verify, keep secrets out of files, stop the agent editing its own guardrails. Pick them and your agent, and install one plugin.
- [Policies](/coding/policies/index.md): every policy shown on this site
- [Builder](/coding/builder/index.md): pick policies, get the command and file
- [Author](/coding/author/index.md): describe a safeguard, get a setup script
- [Install](/coding/install/index.md): the command and the selection file
- [Agents](/coding/clients/index.md): every agent the builder builds for, its --client value, install notes and plugin repository

## Coding agents: policies

- [Agent Discipline](/coding/policies/agent-discipline/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Agentic Code Security](/coding/policies/agentic-code-security/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Agents Started With Safety Off](/coding/policies/block-unguarded-agent-spawn/index.md): blocks, refuses a matched shell command before it runs
- [Block Curl Piped to Shell](/coding/policies/block-curl-pipe-sh/index.md): blocks, refuses a matched shell command before it runs
- [Block Destructive Commands](/coding/policies/block-destructive-commands/index.md): blocks, refuses a matched shell command before it runs
- [Block Files That Skip Git Hooks](/coding/policies/block-hook-bypass-in-files/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Invisible Unicode](/coding/policies/block-invisible-unicode/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Known-Malicious Packages](/coding/policies/compromised-package-ioc/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Persistence and Publishing Commands](/coding/policies/block-persistence-shapes/index.md): blocks, refuses a matched shell command before it runs
- [Block Reading Stored Credentials](/coding/policies/block-secret-store-reads/index.md): blocks, refuses a matched shell command before it runs
- [Block Risky Characters in File and Branch Names](/coding/policies/refname-filename-metachar/index.md): blocks, refuses a matched shell command before it runs. Blocks on an agent's file writes and at turn end
- [Block Skipping Git Hooks](/coding/policies/block-no-verify/index.md): blocks, refuses a matched shell command before it runs
- [Block Test Skips](/coding/policies/block-test-skips/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Unapproved Egress](/coding/policies/block-unapproved-egress/index.md): blocks, refuses a matched shell command before it runs
- [Block Unpinned Agent Components](/coding/policies/block-unpinned-agent-components/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Unsafe Code Execution](/coding/policies/block-unsafe-code-execution/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Unsafe Package Registry Settings](/coding/policies/registry-config/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Weakened Build Hardening](/coding/policies/hardening-flags/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Wildcard Agent Permissions](/coding/policies/block-wildcard-agent-permissions/index.md): blocks, blocks on an agent's file writes and at turn end
- [Block Wildcard IAM Grants](/coding/policies/block-wildcard-iam/index.md): blocks, blocks on an agent's file writes and at turn end
- [CI GitHub Actions Security](/coding/policies/ci-github-actions-security/index.md): blocks, blocks on an agent's file writes and at turn end
- [Code Safety](/coding/policies/code-safety/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Context Hygiene](/coding/policies/context-hygiene/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Dependency Allowlist](/coding/policies/verify-dependency-exists/index.md): blocks, blocks on an agent's file writes and at turn end
- [Dockerfile and Compose Security](/coding/policies/dockerfile-compose-security/index.md): blocks, blocks on an agent's file writes and at turn end
- [EU AI Act — High-Risk Triage](/coding/policies/eu-ai-act-high-risk-triage/index.md): warns, warns on an agent's file writes and at turn end
- [EU AI Act — Prohibited Practices](/coding/policies/eu-ai-act-prohibited-practices/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [EU AI Act — Transparency](/coding/policies/eu-ai-act-transparency/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Flag Dev Tools That Run Code on Open](/coding/policies/agent-devenv-autoexec/index.md): warns, warns on an agent's file writes and at turn end
- [Flag Downloads Run as Code in Files](/coding/policies/block-fetch-exec-in-files/index.md): warns, warns on an agent's file writes and at turn end
- [Flag Hidden Binary Files in Tests](/coding/policies/opaque-blob-guard/index.md): warns, warns on an agent's file writes and at turn end
- [Git Safety](/coding/policies/git-safety/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Guard Deletion and Mitigation Removal](/coding/policies/guard-deletion/index.md): blocks, blocks on an agent's file writes and at turn end
- [Guard Memory Writes](/coding/policies/guard-memory-writes/index.md): blocks, blocks on an agent's file writes and at turn end
- [IAM Policy Scan](/coding/policies/iam-policy-scan/index.md): blocks, blocks on an agent's file writes and at turn end
- [Injection Defense](/coding/policies/injection-defense/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Java Security Rules](/coding/policies/java-security/index.md): blocks, blocks on an agent's file writes and at turn end
- [Keep Accessibility From Regressing](/coding/policies/no-a11y-regression/index.md): blocks, blocks on an agent's file writes and at turn end
- [Keep Changes Small Enough to Review](/coding/policies/limit-diff-size/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Lockfile Integrity](/coding/policies/lockfile-integrity/index.md): blocks, blocks on an agent's file writes and at turn end
- [Match the Owner's Coding Style](/coding/policies/chock-mise/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Memory Discipline](/coding/policies/memory-discipline/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI01 — Agent Goal Hijack](/coding/policies/owasp-asi01-agent-goal-hijack/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI02 — Tool Misuse & Exploitation](/coding/policies/owasp-asi02-tool-misuse/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI03 — Identity & Privilege Abuse](/coding/policies/owasp-asi03-identity-privilege-abuse/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI04 — Agentic Supply Chain Vulnerabilities](/coding/policies/owasp-asi04-agentic-supply-chain/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI05 — Unexpected Code Execution](/coding/policies/owasp-asi05-unexpected-code-execution/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI06 — Memory & Context Poisoning](/coding/policies/owasp-asi06-memory-context-poisoning/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI07 — Insecure Inter-Agent Communication](/coding/policies/owasp-asi07-insecure-inter-agent-communication/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI08 — Cascading Failures](/coding/policies/owasp-asi08-cascading-failures/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI09 — Human-Agent Trust Exploitation](/coding/policies/owasp-asi09-human-agent-trust/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [OWASP ASI10 — Rogue Agents](/coding/policies/owasp-asi10-rogue-agents/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Pin GitHub Actions](/coding/policies/pin-github-actions/index.md): blocks, blocks on an agent's file writes and at turn end
- [Protect Agent Config](/coding/policies/protect-agent-config/index.md): blocks, refuses a matched shell command before it runs. Blocks on an agent's file writes and at turn end
- [Protect CI Workflows](/coding/policies/protect-ci-workflows/index.md): asks, refuses a matched shell command before it runs. Asks on an agent's file writes and at turn end
- [Protect Commit Privacy](/coding/policies/protect-commit-privacy/index.md): blocks, refuses a matched shell command before it runs
- [Protect Main Branch](/coding/policies/protect-main-branch/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Protect Test Integrity](/coding/policies/protect-test-integrity/index.md): blocks, blocks on an agent's file writes and at turn end
- [Review Added Scanner Suppressions](/coding/policies/scan-suppression-markers/index.md): asks, asks on an agent's file writes and at turn end
- [Review Cloud Identity Switches](/coding/policies/ask-credential-switching/index.md): blocks, refuses a matched shell command before it runs
- [Review Like a Red Team](/coding/policies/review-like-a-red-team/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Review Scripts That Run on Install](/coding/policies/package-lifecycle-scripts/index.md): blocks, blocks on an agent's file writes and at turn end
- [Review Values That Look Like Secrets](/coding/policies/scan-secrets-entropy/index.md): asks, asks on an agent's file writes and at turn end
- [Scan Agent Permission Settings](/coding/policies/agent-permissions-scan/index.md): blocks, blocks on an agent's file writes and at turn end
- [Scan Hidden Content](/coding/policies/scan-hidden-content/index.md): warns, warns on an agent's file writes and at turn end
- [Scan Instruction Files](/coding/policies/scan-instruction-files/index.md): blocks, blocks on an agent's file writes and at turn end
- [Scan Secret Files](/coding/policies/scan-secret-files/index.md): blocks, blocks on an agent's file writes and at turn end
- [Scan Secrets](/coding/policies/scan-secrets/index.md): blocks, blocks on an agent's file writes and at turn end
- [Token Efficiency](/coding/policies/token-efficiency/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Use Firecrawl Only as a Fallback](/coding/policies/firecrawl-fallback-only/index.md): advisory, advisory only. It is skill text, and nothing stops a violation
- [Verify MCP Allowlist](/coding/policies/verify-mcp-allowlist/index.md): blocks, refuses a matched shell command before it runs. Blocks on an agent's file writes and at turn end

## Coding agents: presets

- [Git hygiene](/coding/builder/#preset=git-hygiene): Keep hooks on, main protected, commits private and reviewable.
- [Secrets](/coding/builder/#preset=secrets): Keep credentials out of files the agent writes and out of its reach.
- [Packages and supply chain](/coding/builder/#preset=supply-chain): Refuse risky registries, lockfile tampering, known-bad packages and install-time code.
- [CI pipeline](/coding/builder/#preset=ci-pipeline): Pinned actions and safe GitHub Actions workflows.
- [Agent configuration](/coding/builder/#preset=agent-config): Stop the agent widening its own permissions or weakening its guardrails.
- [Prompt injection and memory](/coding/builder/#preset=prompt-injection): Hidden text, injected instructions and poisoned memory.
- [Shell containment](/coding/builder/#preset=shell-containment): Destructive commands, download-and-run, data leaving the machine, persistence.
- [Code hardening](/coding/builder/#preset=code-hardening): Keep compiler hardening, security checks and scanners in place.
- [Test integrity](/coding/builder/#preset=test-integrity): No skipped, weakened or deleted tests to get green.
- [Cloud and containers](/coding/builder/#preset=cloud-iac): Wildcard IAM grants and insecure Dockerfiles or compose files.
- [OWASP agentic top 10](/coding/builder/#preset=owasp-agentic-top10): Guidance for the OWASP top 10 risks of agentic applications.
- [EU AI Act](/coding/builder/#preset=eu-ai-act): Prohibited practices, transparency duties and high-risk triage.
- [Safety guidance](/coding/builder/#preset=safety-guidance): Advice the agent reads on git, code safety, injection and self-review.
- [Agent craft](/coding/builder/#preset=agent-craft): Working habits: verify, keep context clean, remember the right things, save tokens.

## General agents

- [General agents](/general/index.md): design in progress

## Git repositories

- [Git repositories](/repos/index.md): Install policies into your own repository: committed with the code, enforced at commit and in CI for contributors who run `chock sync`, and for agents whose hooks are set up.
- [Set up your repository](/repos/builder/index.md): pick policies, get the commands that install them

## Data

- [/api/index.json](/api/index.json): every section, with its home and api paths
- [/api/coding/catalog.json](/api/coding/catalog.json): every policy and preset (schema_version 1)
- `/api/coding/policies/<id>.json`: one policy record
- [/api/coding/presets.json](/api/coding/presets.json): the presets
- [/api/coding/selection.schema.json](/api/coding/selection.schema.json): the schema a selection file is checked against
- [/api/docs/index.json](/api/docs/index.json): every docs page, and each agent's routes, grade and witness rows
- [/api/docs/search.json](/api/docs/search.json): the docs search index: each page's title, URL, excerpt and headings
- [/api/repos/policies.json](/api/repos/policies.json): each policy's version, sha256 and repository tier, and the catalog commit (schema_version 1)
- [/data/site.json](/data/site.json): the generated site data