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 agentmods add commands/halflength-ampleness75/claude-code-recipes/pr-descriptiongit clone --depth 1 https://github.com/halflength-ampleness75/claude-code-recipesWrote 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/halflength-ampleness75/claude-code-recipes/pr-description)<a href="https://agentmods.dev/commands/halflength-ampleness75/claude-code-recipes/pr-description"><img src="https://agentmods.dev/badge/commands/halflength-ampleness75/claude-code-recipes/pr-description.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00616 |
| Opus 5 | $0.00006 | $0.00308 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
pr-description 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a pull request title and description by analyzing the current branch's changes against the base branch.
Step 1 — Determine the Base Branch
Run git remote show origin or inspect common defaults to determine the base branch. Try main first, then master, then develop. Use whichever exists on the remote.
Step 2 — Gather Context
Run these commands to understand the full scope of changes:
git log --oneline <base>..HEAD— list all commits on this branchgit diff <base>...HEAD --stat— file-level summary of changesgit diff <base>...HEAD— full diff for detailed analysis
Also check if there is a .github/PULL_REQUEST_TEMPLATE.md or similar template file. If one exists, use its structure instead of the default format below.
Step 3 — Analyze the Changes
Read through the diff and commit history to understand:
- What changed (files, functions, components)
- Why it changed (bug fix, new feature, refactor, chore)
- How it changed (approach, patterns, dependencies added/removed)
If commit messages reference issue numbers (e.g., #123, JIRA-456), include them.
Step 4 — Generate the PR Title
Write a concise PR title (under 72 characters) following this format:
feat: add user avatar upload(new feature)fix: resolve race condition in payment processing(bug fix)refactor: extract auth middleware into shared module(refactor)chore: upgrade React from 18 to 19(maintenance)docs: add API authentication guide(documentation)
Use the conventional commit prefix that best matches the changes.
Step 5 — Generate the PR Description
Output the PR description in this format:
## Summary
One to three sentences describing the high-level purpose of this PR.
Reference any related issues: Closes #123, Relates to #456.
## Changes
- Bullet list of specific, meaningful changes
- Group related changes together
- Mention new dependencies, config changes, or migrations
- Note any breaking changes with a **BREAKING:** prefix
## Test Plan
- [ ] Describe how to verify the changes work
- [ ] List any manual testing steps
- [ ] Note which automated tests cover the changes
- [ ] Call out areas that need extra review attention
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.
- 4d ago First seen · 74 lines · 13 tokens per session scan A 5794f04b1565
pr-description is a command published in the GitHub repository halflength-ampleness75/claude-code-recipes (2 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 616 once invoked, about $0.0001 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
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
help
Explain Ralph Wiggum technique and available commands.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.