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 iCodeCraft/anti-slop --skill pr-hygienegit clone --depth 1 https://github.com/iCodeCraft/anti-slopWrote 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/icodecraft/anti-slop/pr-hygiene)<a href="https://agentmods.dev/skills/icodecraft/anti-slop/pr-hygiene"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/pr-hygiene/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/icodecraft/anti-slop/pr-hygiene"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/pr-hygiene.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 | $0.00057 | $0.00414 |
| Opus 5 | $0.00028 | $0.00207 |
| Sonnet 5 | $0.00011 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
pr-hygiene 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.
What it actually says
PR Hygiene
Turn the current work into a PR a human can review in one pass.
Before opening
- Branch contains one logical change (or clearly labeled stacked commits)
- No leftover
console.log,debugger,TODO: temp, commented-out blocks you added - No unrelated formatting-only churn
- Secrets,
.env, and local-only files are not staged - Diff matches the stated goal — nothing "extra helpful"
Description template
Use this structure (adapt section names to the host: GitHub/GitLab):
## Summary
<1–3 bullets: what and why>
## Test plan
- [ ] <how you verified>
- [ ] <edge case worth checking>
## Notes
<risks, follow-ups, screenshots if UI>
Commit / PR title
- Imperative, specific:
fix checkout: reject expired discount codes - Not:
update stuff,fix,WIP,address comments
Reviewer empathy
Call out:
- Files that look scary but are mechanical (renames, generated)
- Behavior that changed for callers/API consumers
- Anything you are unsure about
Anti-patterns
- NEVER mix refactor + feature + dependency bump in one PR unless required
- NEVER force-push shared branches without warning
- NEVER open a PR with "tests TBD" and no plan
- NEVER bury breaking changes in the middle of the description
If asked to open the PR
- Summarize the diff in your own words first
- Draft title + body with the template
- List residual risks in one short section
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 · 59 lines · 57 tokens per session scan A c64d6f6c2160
pr-hygiene is a skill published in the GitHub repository iCodeCraft/anti-slop (27 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 414 once invoked, about $0.0003 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
wednesday-git
Unified Git workflow. Manages the entire task lifecycle: branch creation (sprint), atomic commits (git-os), and PR opening (pr-create).
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
issue-reporter
A tool for submitting a GitHub Issue, Bug Report, or Feature Request when the user explicitly asks for one. A GitHub Issue is a tracked report or request in a software project.