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 0x0w1/jig --skill jig-conformance-auditgit clone --depth 1 https://github.com/0x0w1/jigWrote 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/0x0w1/jig/jig-conformance-audit)<a href="https://agentmods.dev/skills/0x0w1/jig/jig-conformance-audit"><img src="https://agentmods.dev/badge/skills/0x0w1/jig/jig-conformance-audit/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/0x0w1/jig/jig-conformance-audit"><img src="https://agentmods.dev/badge/skills/0x0w1/jig/jig-conformance-audit.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 | $0.00067 | $0.01413 |
| Opus 5.5 | $0.00027 | $0.00565 |
| Sonnet 5.5 | $0.00013 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
jig-conformance-audit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- conformance-audit — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conformance Audit
Use this repository skill to verify after the fact that the procedure was followed. The push guards stop a bad push while it happens; nothing else checks that what did land matches the rules.
Three skills look at a repository and none of them overlap:
| Skill | Subject | Writes |
|---|---|---|
jig-doctor |
the jig installation | nothing |
repo-hygiene |
debris in the local clone | deletes what the user names |
conformance-audit |
the history the procedure produced | nothing |
This one never edits, deletes, or rewrites anything. Its output is a report and an exit code.
Why a Baseline
A repository that installs jig today has years of history written under other rules. Judging all of it reports the repository as broken on day one and teaches the user to ignore the tool.
Every run therefore starts from a baseline and judges nothing before it:
--since <ref>when the user names one.- The commit that added
.jig/versioning.md— the point the repository adopted the grading contract. - The oldest
vX.Y.Ztag. - Nothing resolves → stop with a usage error. Never fall back to the whole history.
Always report which baseline was used and where it came from. A finding means nothing without it.
What a Missing Grade Costs
develop-task-flow records a Release-Grade trailer at merge, and github-release reads the highest one in the release range as a floor it never lowers.
When no commit in the range carries a trailer, that lookup returns an empty string. The release does not fail and does not warn; it silently grades from the advisory path floor alone, which says what was touched and never how. A repository can ship many versions that way without one visible symptom.
That is why zero coverage is a violation while partial coverage is only a note: partial adoption is a repository mid-migration, zero is a floor that no longer exists.
Checks
| ID | What it looks for | Level |
|---|---|---|
subject-prefix |
commits with no conventional type | violation |
subject-type |
a type outside feat, fix, chore, docs, refactor, test, ci |
note |
grade-coverage |
no Release-Grade in the release range (partial → note) |
violation |
grade-value |
a trailer that is not one lowercase patch, minor, or major |
violation |
tag-format |
tags outside ^v[0-9]+\.[0-9]+\.[0-9]+$ |
violation |
tag-on-main |
a version tag main cannot reach |
violation |
main-ancestry |
main is not an ancestor of develop |
violation |
main-lineage |
commits on main that develop cannot reach |
violation |
rubric-tracked |
the rubric is missing, untracked, or uncommitted | note |
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 · 106 lines · 67 tokens per session scan A c5b991046728
jig-conformance-audit is a skill published in the GitHub repository 0x0w1/jig (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,413 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 2026-09-03.
Other skills, from other repositories
git-ship
An automated Git release workflow that takes code changes through a branch, commit, pull request, review checks, squash merge, and return to the main branch. A pull request is a request to review and merge changes into a shared branch.
semantic-release-convention-skill
Source of truth for commit-to-PR-to-merge-to-release conventions — semver labels, branch-aware tagging, changelogs, release pipelines.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.