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 45ck/skill-harness --skill noslop-commit-gategit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/noslop-commit-gate)<a href="https://agentmods.dev/skills/45ck/skill-harness/noslop-commit-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/noslop-commit-gate/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/45ck/skill-harness/noslop-commit-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/noslop-commit-gate.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 | $0.00030 | $0.00649 |
| Opus 5.5 | $0.00012 | $0.00260 |
| Sonnet 5.5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
noslop-commit-gate 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.
What it actually says
Use this skill before every git commit in a noslop-protected repository.
Gate command:
noslop check --tier=fast
Run this before staging the final commit. The pre-commit hook runs it automatically, but running it manually first surfaces failures early.
If the gate fails:
- read the failure output and fix the reported issue (lint error, format violation, spell error)
- never use
git commit --no-verify— the Claude Code guardrails block this for AI agents and it defeats the purpose of the gate - never disable lint rules to make the gate pass; fix the underlying issue
- after fixing, re-run
noslop check --tier=fastto confirm the gate is green before committing
Content-aware config protection — Tier 1:
The pre-commit hook checks quality gate config files for weakening patterns. Strengthening changes pass through automatically.
| Config | Blocked (weakening) | Allowed (strengthening) |
|---|---|---|
eslint.config.mjs |
Adding 'off' rules, eslint-disable, net removal of 'error' rules |
New rules, tighter limits |
vitest.config.ts |
Lowering coverage thresholds, removing thresholds | Raising thresholds |
tsconfig*.json |
Adding strict: false, net removal of strict flags |
New strict flags |
.dependency-cruiser.cjs |
Net removal of name: rules, severity downgrade to warn/info/off |
New forbidden rules |
knip.json |
Expanding ignore/ignoreDependencies, ignoreExportsUsedInFile |
New entry points |
Enforcement file protection — Tier 2a:
Files in .githooks/, .claude/hooks/, and AGENTS.md are the enforcement mechanism itself. The hook only blocks:
- removal of quality commands (
npm run ci,npm run test,noslop check, etc.) - net removal of
exit 1lines - net removal of
set -elines
Additive changes (new jobs, new checks, new schedules) pass through.
CI and config file protection — Tier 2b:
Files in .github/workflows/ and .claude/settings.json are fully checked:
- removal of quality commands
- addition of bypass patterns (
continue-on-error: true,--no-verify,[skip ci],SKIP_CI,skip-checks) - net removal of
exit 1
Lines containing deny, block, or "Bash are excluded from bypass detection to avoid false positives on enforcement logic.
Avoid:
- using
--no-verifyunder any circumstance - adding
eslint-disablecomments to silence lint failures - downgrading config severity to pass the gate
- editing
.githooks/,.claude/, or.github/workflows/to remove gate commands
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 · 61 lines · 30 tokens per session scan A 4a3ce4996a46
noslop-commit-gate is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 649 once invoked, about $0.0001 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-edit-commit
Use when needing to fixup, squash, drop, reword, reorder, or edit commits in a branch's history. Handles the non-interactive approach agents need since git rebase -i requires a TTY.
git-atomic-commit
Use when splitting a working tree into atomic commits, or when changes need to be distributed across new commits and/or edits to prior commits on the branch. Especially relevant when changes within a single file belong in different commits.
git-commit
Use when creating Git commits.
enable-review
Turn interactive commit reviews back on for the current herdr workspace.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.