CC Safety Net is a pre-execution guard that analyzes coding-agent tool calls and blocks destructive commands or attempts to access sensitive files. It is for people using supported coding-agent command-line tools on Windows, macOS, or Linux. The catalogue entries provide its safety rules, instructions, hook, and plugin.
Borrowing it
Nothing to install: this file belongs to kenryu42/cc-safety-net. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kenryu42/cc-safety-net/main/AGENTS.mdgit clone --depth 1 https://github.com/kenryu42/cc-safety-netWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kenryu42/cc-safety-net/agents-md)<a href="https://agentmods.dev/instructions/kenryu42/cc-safety-net/agents-md"><img src="https://agentmods.dev/badge/instructions/kenryu42/cc-safety-net/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kenryu42/cc-safety-net/agents-md"><img src="https://agentmods.dev/badge/instructions/kenryu42/cc-safety-net/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02158 | $0.02158 |
| Opus 5.5 | $0.00863 | $0.00863 |
| Sonnet 5.5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
cc-safety-net AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Before filing an issue, read
CONTRIBUTING.mdand follow its reporting rules. - Run focused tests during development, including the reproducing test for a behavior change.
- After all implementation changes, run
bun run check. This is the required final check for lint, code comments, formatting, typecheck, knip, duplication, and tests. Do not run its components separately as additional final checks. A change that touches only Markdown skips it, as the pre-push hook and CI do, unless it touchesskills/cc-safety-net/SKILL.mdorREADME.md: the build bundles the skill intodist/, and tests read both. - Ignore the dist folder; it gets auto-rebuilt by lefthook's pre-commit hook.
- Keep implementation modular; put tests in
tests/mirroringsrc/, not colocated insrc/. - Files in
docs/use lowercase kebab-case names.
Stacked PRs
- Multi-part work may be split into a
gh stackstack. Open stack PRs withgh stack submit --auto --open: plain--autoopens drafts, which the review bots skip. dist/is committed and CI rejects a stale build, but a rebase replays the old build output. Whengh stack rebasestops, resolve andgit addthe source files, never hand-mergedist/: runbun run build && git add -A dist, thengh stack rebase --continue.
CI failures
Reproduce a failing ci.yml step locally before pushing a fix:
- Check source →
bun run check. - Verify E2E stability →
bun run test:e2e:stability. A failure here is usually a flaky test: fix the flake, never re-run CI to get green. - Reject stale generated artifacts →
bun run build && git diff --exit-code -- dist, then commit the regenerateddist/. - Verify package surfaces →
bun run verify:repository-plugin && bun run verify:package. - Audit all dependencies →
bun run audit:dependencies. - packed-runtime →
bun run build && bun run verify:package; the failed log names the Node version. - full-check-windows has no local repro on macOS: read
gh run view <run-id> --log-failed, or reproduce on a probe branch as Windows verification describes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago Changed · +6 tokens per session f0d38c530e4d
- 12d ago Changed · +18 lines · +284 tokens per session 4e35d870b1f7
- 19d ago Changed · +26 lines · +470 tokens per session 70dcea6d9eb9
- 21d ago Changed · +1 lines · +20 tokens per session 008277ccad76
- 24d ago Changed · +12 lines · +164 tokens per session afa3ab827a4f
- 28d ago Changed · +12 lines · +190 tokens per session 0180379771d1
- 1mo ago Changed · +8 lines · +127 tokens per session ff21406ae7c9
- 1mo ago Changed · +3 tokens per session 041748f4e7f0
- 1mo ago Changed · +12 lines · +174 tokens per session 0a00d13d5d2d
- 1mo ago First seen · 45 lines · 720 tokens per session scan A 1d14352c9027
cc-safety-net AGENTS.md is an instructions file published in the GitHub repository kenryu42/cc-safety-net (1,798 stars, last pushed today), licensed MIT. It adds 2,158 tokens to every session, about $0.0086 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.