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 jason21wc/ai-governance-mcp --skill all-cleargit clone --depth 1 https://github.com/jason21wc/ai-governance-mcpWrote 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/jason21wc/ai-governance-mcp/all-clear)<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/all-clear"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/all-clear/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/jason21wc/ai-governance-mcp/all-clear"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/all-clear.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 | $0.00099 | $0.01553 |
| Opus 5 | $0.00049 | $0.00776 |
| Sonnet 5 | $0.00020 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
all-clear scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Read procedure.md in this skill folder and follow it in order.
Resolve the date, repository, and worktree list with ordinary read-only commands when needed. Do not use Claude Code's bang-backtick inline-injection syntax here (an exclamation mark immediately followed by a backtick-quoted command); Codex renders it as literal text, and Claude Code EXECUTES it at load — including inside a code span, which is why this sentence describes the syntax rather than showing it. Writing it out, even quoted, arms it.
The load-bearing step is allclear.sh, which ships beside procedure.md. Run it and
report its exit code. Do not substitute your own reasoning for it — the entire reason
this skill exists is that a hand-written "nothing pending" rots the moment it is written,
and an agent re-deriving the checks from memory reproduces exactly that failure.
AC=~/.claude/skills/all-clear/allclear.sh
[ -f "$AC" ] || AC=~/.codex/skills/all-clear/allclear.sh
bash "$AC"
# 0 = all clear — every check ran, nothing outstanding
# 1 = findings — something is uncommitted, unpushed, unlanded, or left behind
# 2 = undetermined — a check could not run. NOT clear. The human decides.
# 3 = not a git repository
# anything else (127 = script not found) — stop and say so
If allclear.sh cannot be found, stop and tell the user. Do not improvise the
checks by hand.
Key Principles
- Three axes, and conflating any two is the defect this exists to catch. Clean =
nothing uncommitted. Durable = the commits exist off this disk. Landed = the
commits reached the branch everyone else reads. None implies another.
cleanup.shonce checked durability and reported it as safe-to-remove, so a branch that was pushed and never merged was removed with its local branch deleted — the work survived only on a remote ref nothing tracked. - Durability is nearly free here, so it is the weakest signal.
start-worktreestep 4c publishes every branch at creation to reserve the name. Every worktree branch is therefore durable from birth, which is precisely why durability alone could never fail for the workflow it was supposed to guard. - Compute it; never recall it. Every finding is derived from
gitat the moment you ask. This repo's scar is a memory file reading "ACTION ON RESUME: nothing pending" while two stale branches, an orphan worktree, two unpushed tags, an open PR and five unpushed commits accumulated behind it. - Presence is not a finding. A worktree whose lock PID is alive belongs to a session that is still working. It is reported, it is counted in the summary, and it does not make the verdict red. A checker that flags a busy teammate as residue gets tuned out.
- Duplicate task intent is a fleet finding, not a deletion license. V2 journals expose task keys across otherwise-isolated worktrees. Unexpected duplicates make the report non-green; explicit parallel intent remains visible. Neither case authorizes cleanup, and legacy same-slug candidates are labelled ambiguous rather than guessed.
- Ancestry lies — so report evidence, never a verdict. After a rebase or squash,
--no-mergedwill call a fully-landed branch unmerged. This skill offers a merge command and agit loghandle for unlanded work. It never offers a delete command, in either direction. - An unrun check is not a passed check — but say which checks you claim. Failure to
resolve a default branch makes merge state unknown for everything, so that returns 2.
Open PRs and unpushed tags are surfaces
repo_hygiene.pyowns; where that script is absent the report says so out loud and scopes its verdict, rather than either pretending it looked or refusing to ever go green. - It must be possible to go green. A check that can never pass stops being read, and then the one time it matters nobody looks.
What ships with it
2 files 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.
- 11d ago First seen · 97 lines · 99 tokens per session scan A 4ca22f6cfcdf
all-clear is a skill published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,553 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…