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.
git clone --depth 1 https://github.com/mertjane/awesome-claude-commandsWrote 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/commands/mertjane/awesome-claude-commands/pr-desc)<a href="https://agentmods.dev/commands/mertjane/awesome-claude-commands/pr-desc"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/pr-desc/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/commands/mertjane/awesome-claude-commands/pr-desc"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/pr-desc.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 | $0.00034 | $0.00957 |
| Opus 5 | $0.00017 | $0.00478 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
pr-desc 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Pull Request Description
Analyze the current branch's changes and produce a ready-to-paste GitHub pull request description.
Base branch: use $ARGUMENTS if provided, otherwise default to main. If main does not exist, try master or develop.
Step 1 — Gather Branch Info
Run:
git rev-parse --abbrev-ref HEAD
to get the current branch name.
Run:
git log {base}..HEAD --oneline
to list all commits since branching off.
Run:
git diff {base}...HEAD --stat
to get a summary of changed files and line counts.
Run:
git diff {base}...HEAD
to get the full diff for analysis.
If git is not available or the repo has no commits, report and stop.
Step 2 — Classify Changes
Read the diff and categorize every changed file:
| Category | Detection |
|---|---|
| feat | New files added; new exported functions/components/routes |
| fix | Changes inside existing functions that correct logic |
| refactor | Renames, moves, restructured code with same behavior |
| style | CSS/Tailwind changes, formatting-only changes |
| test | Files in __tests__, *.test.*, *.spec.* |
| docs | .md, .txt, docs/ changes |
| chore | Config files, package.json, tsconfig, CI/CD |
| perf | Optimizations, memoization, caching, query improvements |
A PR can contain multiple categories. List all that apply.
Step 3 — Summarize Changes
For each changed file or logical group:
- What was added (new functionality, new files, new exports)
- What was changed (updated logic, renamed, restructured)
- What was removed (deleted files, removed exports, cleanup)
Keep descriptions short and factual. Do not speculate on intent.
Step 4 — Detect Scope and Impact
Identify:
- Breaking changes: removed exports, changed function signatures, renamed routes/endpoints, updated env var names
- Dependencies changed:
package.jsonadditions/removals - Database changes: new migrations, schema changes
- API changes: new/modified/removed endpoints
- Security-relevant changes: auth, permissions, input validation
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.
- 10d ago First seen · 140 lines · 34 tokens per session scan A 0477afa278ab
pr-desc is a command published in the GitHub repository mertjane/awesome-claude-commands (2 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 957 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 2026-08-31.
Other commands, from other repositories
pr
Create a pull request using the git-pushing skill.
implement
Feature implementation in a repo — ticket → plan gate → develop-to-plan → draft-PR review loop (human gate) → squash-clean finalize. Thin recipe over six overridable primitives; dossier-mcp the only hard dependency.
ship
Prepare the current branch for review and deployment.
ship
Seen on their staging, then live. Rollback you have run.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).