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-pr-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-pr-gate)<a href="https://agentmods.dev/skills/45ck/skill-harness/noslop-pr-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/noslop-pr-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-pr-gate"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/noslop-pr-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 | $0.00033 | $0.00571 |
| Opus 5 | $0.00016 | $0.00285 |
| Sonnet 5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
noslop-pr-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 9d 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 opening or updating a pull request in a noslop-protected repository.
Gate command:
noslop check --tier=slow
Run this after all commits are staged and before opening the PR. This tier runs type checking and the full test suite. The pre-push hook runs it automatically before git push, but running it manually first avoids a rejected push.
If the gate fails:
- fix the type error or test failure reported in the output
- never use
[skip ci],skip-checks, orSKIP_CIin commit messages or CI configuration - never add
continue-on-error: trueto workflow steps to force a green CI run - re-run
noslop check --tier=slowto confirm the gate is green before pushing
Escape hatch for intentional weakening:
If a change intentionally weakens a quality gate config (for example, removing an obsolete lint rule), the pre-commit hook will block it locally. To proceed:
- submit the change via a pull request
- have a human reviewer apply the
noslop-approvedlabel to the PR guardrails.ymlenforces the label requirement; the PR cannot merge without it
This escape hatch is for deliberate, reviewed decisions only. Do not use it to unblock failing gates. Do not apply the label yourself.
Protected files requiring the label:
.githooks/.github/workflows/.claude/settings.json.claude/hooks/
Any PR that modifies these paths without the noslop-approved label will be blocked by the guardrails CI check.
CI is authoritative:
The quality.yml workflow runs --tier=ci (all tiers combined) on every PR and every push to main. It is configured as a required status check. Bypassing local hooks does not bypass CI. The CI tier is the final gate and cannot be skipped by any local trick.
Checklist before opening a PR:
noslop check --tier=slowpasses locally- no
[skip ci],SKIP_CI, orskip-checksin commit messages - no
continue-on-error: trueadded to workflows - if protected files are modified, the
noslop-approvedlabel has been applied by a human reviewer
Avoid:
- pushing with
--forcewithout explicit human approval - adding CI-bypass patterns to get a failing check to pass
- requesting or applying the
noslop-approvedlabel without a human reviewer's explicit decision
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.
- 9d ago First seen · 58 lines · 33 tokens per session scan A f8532fe6aac0
noslop-pr-gate is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 571 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
code-review
Code review assistance with linting, style checking, and best practices.
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
cross-review
Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…