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 lc-rezende/AI-Custom-Skills --skill git-pr-helpergit clone --depth 1 https://github.com/lc-rezende/AI-Custom-SkillsWrote 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/lc-rezende/ai-custom-skills/git-pr-helper)<a href="https://agentmods.dev/skills/lc-rezende/ai-custom-skills/git-pr-helper"><img src="https://agentmods.dev/badge/skills/lc-rezende/ai-custom-skills/git-pr-helper/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/lc-rezende/ai-custom-skills/git-pr-helper"><img src="https://agentmods.dev/badge/skills/lc-rezende/ai-custom-skills/git-pr-helper.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 | $0.00031 | $0.00446 |
| Opus 5 | $0.00015 | $0.00223 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
git-pr-helper 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
Git PR Helper
Generate pull request titles and bodies from branch changes.
When to use this skill
- The user is about to open a pull request
- The user asks for a PR title or PR body
- A PR description is requested
Workflow
- Review the branch changes and recent commits.
- Identify the primary intent, scope, and impact of the change.
- Draft a concise PR title in imperative mood.
- Draft a PR body using the standard sections below.
- Ask if any context, validation, or notes should be adjusted.
PR title guidelines
- Use imperative mood ("add", "fix", "update")
- Keep it concise (max 72 characters)
- Describe what and why, not how
- No trailing period
PR body format
## Summary
- <1-3 bullet points of the change>
## Validation
- <tests or checks run, or "Not run">
## Notes
- <optional context, risks, or follow-ups>
Examples
Feature PR
Title:
add skill validation workflow for branches
Body:
## Summary
- add GitHub Actions workflow to validate skills
- run checks on pushes and pull requests
## Validation
- Not run (CI only)
## Notes
- None
Fix PR
Title:
fix workflow output delimiter for validation report
Body:
## Summary
- fix multiline output formatting for report step
## Validation
- Not run (CI only)
## Notes
- None
Refactor PR
Title:
refactor skill templates for clearer examples
Body:
## Summary
- reorganize sample skills for readability
- align examples with current conventions
## Validation
- Not run (docs only)
## Notes
- None
Output expectations
- Provide a PR title and full PR body.
- Keep the summary factual and concise.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 109 lines · 31 tokens per session scan A ea0fe3c0f4e2
git-pr-helper is a skill published in the GitHub repository lc-rezende/AI-Custom-Skills (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 446 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 skills, from other repositories
shared-tooling-changesets
Versioning and changelog management with @changesets/cli — adding changesets, version bumping, changelog generation, monorepo publishing, pre-release modes, and CI automation.
shared-tooling-git-hooks
Husky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8.
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
git-commit
Create well-structured git commits using the Conventional Commits specification. Use when asked to "commit changes", "create a git commit", "stage and commit", "write a commit message", or "/commit". Analyzes diffs to auto-detect type and scope, generates semantic commit messages, and supports intelligent file staging.
git-workflow
Consistent git practices, recovery patterns, and safe operations.
github-wiki-flat
GitHub Wiki has a flat namespace — no real folders, sidebar ordering tricks, link gotchas.