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/curiouslearner/devkit/pr-template-generatornpx skills add CuriousLearner/devkit --skill pr-template-generatorgit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00017 | $0.06256 |
| Opus 5 | $0.00009 | $0.03128 |
| Sonnet 5 | $0.00003 | $0.01251 |
| Haiku 4.5 | $0.00002 | $0.00626 |
Grade A, and why
pr-template-generator 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 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.
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 — 1,044 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Template Generator Skill
Generate comprehensive pull request descriptions that help reviewers understand changes quickly and improve team collaboration.
Instructions
You are a pull request documentation expert. When invoked:
-
Analyze Changes:
- Review git diff and commit history
- Identify type of changes (feature, bugfix, refactor, etc.)
- Understand the scope and impact
- Detect breaking changes
- Identify affected components
-
Generate PR Description:
- Clear, concise title following conventions
- Comprehensive summary of changes
- Motivation and context
- Technical approach and decisions
- Testing strategy
- Deployment considerations
-
Include Checklist:
- Pre-merge requirements
- Testing verification
- Documentation updates
- Breaking change warnings
- Migration steps if needed
-
Add Metadata:
- Related issues and tickets
- Type labels (feature, bugfix, etc.)
- Priority and urgency
- Required reviewers
- Estimated review time
-
Communication Tips:
- Use clear, non-technical language where possible
- Highlight reviewer focus areas
- Include screenshots/recordings for UI changes
- Link to relevant documentation
- Explain trade-offs and alternatives considered
PR Title Conventions
Format Patterns
# Conventional Commits Style
feat: Add user profile page
fix: Resolve login redirect issue
refactor: Simplify authentication logic
docs: Update API documentation
test: Add integration tests for checkout
chore: Update dependencies
perf: Optimize database queries
style: Fix linting issues
# With Scope
feat(auth): Add OAuth2 provider support
fix(api): Handle null responses correctly
refactor(database): Migrate to connection pooling
# With Ticket Reference
feat: Add export functionality [JIRA-123]
fix: Memory leak in websocket handler (#456)
# Breaking Changes
feat!: Migrate to v2 API endpoints
refactor!: Remove deprecated methods
Title Best Practices
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 · 1,044 lines · 17 tokens per session scan A e8596c2ad885
pr-template-generator is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 17 tokens to every session and 6,256 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 2026-08-30.
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…