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 MuhammadUsmanGM/claude-code-best-practices --skill pr-describegit clone --depth 1 https://github.com/MuhammadUsmanGM/claude-code-best-practicesWrote 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/muhammadusmangm/claude-code-best-practices/pr-describe)<a href="https://agentmods.dev/skills/muhammadusmangm/claude-code-best-practices/pr-describe"><img src="https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/pr-describe/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/muhammadusmangm/claude-code-best-practices/pr-describe"><img src="https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/pr-describe.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 | $0.00044 | $0.00470 |
| Opus 5.5 | $0.00018 | $0.00188 |
| Sonnet 5.5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
pr-describe 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
PR Describe
Draft a pull-request title and body. Do not open the PR — hand the text to the user.
Steps
- Detect the base branch: check
git remote show origin | grep 'HEAD branch', fall back tomain. git log <base>..HEAD --no-merges --reverse --format='%h %s%n%b'— read every commit, not just the latest.git diff <base>...HEAD --statfor scope, then targetedgit diff <base>...HEAD -- <path>for files that look important.- If a PR template exists at
.github/pull_request_template.mdor.github/PULL_REQUEST_TEMPLATE.md, follow its structure.
Title
- ≤ 70 characters, imperative mood, no trailing period.
- Prefix with a Conventional Commits type only if the repo's existing PR titles do.
Body
Default structure (unless a template overrides):
## Summary
<2-4 bullets: what changed and why — not a commit list>
## Changes
<grouped, human-readable bullets; collapse noisy refactors>
## Test plan
- [ ] <explicit verification step>
- [ ] <explicit verification step>
## Notes
<risks, migrations, follow-ups — omit the section if empty>
Rules
- Focus on why, not what. The diff already shows what.
- Never invent issue numbers or Jira tickets. Only include
Closes #Nif a commit message references it. - If the branch is empty relative to base, stop and tell the user.
- Do not run
gh pr createor push. Output the title and body as a single markdown block the user can paste.
Output
Exactly two fenced blocks: title and body. Nothing else.
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 · 52 lines · 44 tokens per session scan A bff5d4ce4ac5
pr-describe is a skill published in the GitHub repository MuhammadUsmanGM/claude-code-best-practices (98 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 470 once invoked, about $0.0002 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
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.