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 skills/justrach/codegraff2/github-pr-descriptionnpx skills add justrach/codegraff2 --skill github-pr-descriptiongit clone --depth 1 https://github.com/justrach/codegraff2What 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 | $0.00072 | $0.02411 |
| Opus 5 | $0.00036 | $0.01205 |
| Sonnet 5 | $0.00014 | $0.00482 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
github-pr-description scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:3000/search \ This is a copy
100% identical to github-pr-description — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR Description
Generate comprehensive pull request descriptions and create PRs using GitHub CLI.
Workflow
1. Verify Prerequisites
Check that there are changes to create a PR for:
# Get current branch
git branch --show-current
# Verify branch is not main/master
# Verify there are commits ahead of main
git log origin/main..HEAD --oneline
If on main/master or no commits ahead, inform the user there's nothing to create a PR for.
2. Analyze Changes
Gather context about the changes:
# Get commit messages
git log origin/main..HEAD --pretty=format:"%s"
# Get diff summary (files changed)
git diff origin/main..HEAD --stat
# Get actual code changes (sample key files if diff is large)
git diff origin/main..HEAD
For large diffs: Focus on the most meaningful changes. Sample key files rather than reading everything.
3. Determine Change Type
Classify the PR into one of these categories:
- fix: Bug fixes, error corrections, resolving issues
- feature: New functionality, capabilities, or enhancements
- performance: Speed improvements, optimization, efficiency gains
- refactor: Code restructuring without changing behavior
- docs: Documentation changes
- test: Test additions or improvements
- chore: Maintenance tasks, dependencies, configuration
Base this on:
- Commit messages (keywords like "fix", "add", "optimize", "refactor")
- Nature of code changes (new files = feature, test fixes = fix, etc.)
- Scope of changes
4. Generate Description
Create a comprehensive description with this structure:
## Summary
[One sentence explaining what this PR does and why it matters]
## Context
[Background information, related issues, previous work, or the problem being solved]
## Changes
[High-level description of what changed]
### Key Implementation Details
[Technical details that help reviewers understand the approach, especially for complex changes]
## Use Cases
[Concrete examples of how this will be used - helps reviewers understand practical value]
## Testing
[How to test the changes - step-by-step instructions]
## Links
- Related issues: #123, #456
- Documentation: URL (if applicable)
- Original implementation: URL (if applicable)
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.
- 2d ago First seen · 351 lines · 72 tokens per session scan A 0eb8bfd663f0
github-pr-description is a skill published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,411 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to github-pr-description, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…