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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kenryu42/cc-safety-net --skill release-notesgit 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/skills/kenryu42/cc-safety-net/release-notes)<a href="https://agentmods.dev/skills/kenryu42/cc-safety-net/release-notes"><img src="https://agentmods.dev/badge/skills/kenryu42/cc-safety-net/release-notes/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/skills/kenryu42/cc-safety-net/release-notes"><img src="https://agentmods.dev/badge/skills/kenryu42/cc-safety-net/release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.02930 |
| Opus 5.5 | $0.00026 | $0.01172 |
| Sonnet 5.5 | $0.00013 | $0.00586 |
| Haiku 4.5 | $0.00006 | $0.00293 |
Grade A, and why
release-notes 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 1mo 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes
Update only the body of the latest existing GitHub Release. Treat the repository diff as the source of truth. Use pull requests and commits only as supporting evidence.
Safety rules
- Use
ghfor all GitHub Release, pull request, issue, and API operations. Usegit fetchonly when required tag objects or history are missing. - Do not create or delete a release.
- Do not change a tag, title, target, draft state, prerelease state, latest-release state, or other release metadata.
- Do not publish a draft.
- Do not use a new release as a fallback when no release exists.
- Do not infer release order from version text, semantic versions, or Git tag order.
- Stop when required evidence is unavailable. Do not publish partial or speculative notes.
- Treat the notes file as a full replacement for the current release body, not as text to append.
1. Verify prerequisites
Run all checks from the repository that the user wants to release:
-
Confirm that the current directory is in a Git worktree:
git rev-parse --is-inside-work-tree -
Confirm that
ghis available:command -v gh -
Confirm that
ghcan resolve and access the current GitHub repository. Save its URL and get the GitHub host from it:REPO_URL="$(gh repo view --json url --jq '.url')" GH_HOSTNAME="${REPO_URL#*://}" GH_HOSTNAME="${GH_HOSTNAME%%/*}" -
Use the repository URL to get its GitHub host. Confirm the active account for that host:
gh auth status --active --hostname "$GH_HOSTNAME"
Stop with a clear error if a check fails. Do not initialize a Git repository, change authentication, or select another repository as a fallback.
2. Select the release range
Use GitHub's descending release-list order as the release sequence. Include drafts and prereleases because they are existing releases:
gh release list --limit 2 --order desc \
--json tagName,name,createdAt,publishedAt,isDraft,isPrerelease,isImmutable,isLatest
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 289 lines · 65 tokens per session scan A 37f3181c7f9f
release-notes is a skill published in the GitHub repository kenryu42/cc-safety-net (1,656 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 2,930 once invoked, about $0.0003 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 skills, from other repositories
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
commit-optimization
Use when configuring settings.json to reduce fuse-commit-pro's context token usage.
release
Automates the full release workflow: version bump, git tag, GitHub release, and npm publish.
find
Find the local coding-agent session that wrote the uncommitted changes in a file, or in a pasted snippet of changed code or comment text, and give a one-line command that resumes it. Prefers the session that authored the change over a review session. Use when asked which session, chat, thread, or agent made an edit…
pickup
Resume work in a fresh session from the newest handoff file written by /handoff, from a named handoff file, or from an unfinished orchestration run found on a local feature branch. Checks first whether commits made after the handoff already did its task.