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/crypticswarm/swarmforge/commit-messagesnpx skills add CrypticSwarm/Swarmforge --skill commit-messagesgit clone --depth 1 https://github.com/CrypticSwarm/SwarmforgeWhat 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 | $0.00040 | $0.01478 |
| Opus 5 | $0.00020 | $0.00739 |
| Sonnet 5 | $0.00008 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
commit-messages 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 yesterday.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Messages
Use this workflow whenever you need to write or review a Git commit message.
Response discipline: When fulfilling this skill, output only the commit message text (subject line plus optional body) and nothing else.
Agent workflow
Aim for messages that help a reviewer (often future you) understand intent.
- Identify the user-visible intent (what changes when applied).
- If the diff includes multiple changes, pick the primary feature/outcome.
- Draft an imperative subject that leads with that primary feature.
- Heuristic:
Verb + user-facing object + benefit
- Heuristic:
- Add a body to capture secondary context (enablers, constraints, risk).
- Ensure the commits in a PR "tell a story" (each subject advances it).
- Re-check for clarity without reading the diff.
Format
Subject line (first line)
- Capitalize the first word.
- Keep it short: aim for 50 characters or less.
- Lead with the primary user-visible feature/outcome.
- Prefer:
Persist session data between runs - Avoid:
Prepare host dirs for Docker run
- Prefer:
- Use the imperative mood (describe what the commit does when applied):
- Good:
Add caching to user lookup - Bad:
Added caching to user lookup - Bad:
Adds caching to user lookup
- Good:
- No trailing period.
Blank line
- Always put a blank line after the subject.
- Omit the body entirely if it adds no value, but keep the blank line rule when a body exists.
Body (optional)
- Wrap paragraphs to ~72 columns.
- Focus on why and impact (rationale, constraints, tradeoffs, risk).
- Use the body for secondary details (enabling work, implementation notes, migration, risk) so the subject can stay feature-first.
- Prefer intent and constraints over a narration of the diff.
- Answer at least one of:
- Why was this necessary?
- What behavior changed (user-visible or system-level)?
- What alternatives were considered and rejected?
- What risks or follow-ups exist?
- Link to relevant context when available (issue/PR/ticket IDs).
- Separate paragraphs with blank lines.
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.
- yesterday First seen · 194 lines · 40 tokens per session scan A 4015721d06cb
commit-messages is a skill published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,478 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
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…