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/dentiny/kon/commit-messagenpx skills add dentiny/kon --skill commit-messagegit clone --depth 1 https://github.com/dentiny/konWhat 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 | $0.00050 | $0.00626 |
| Opus 5 | $0.00025 | $0.00313 |
| Sonnet 5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
commit-message 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message
Consumers: any task that drafts a commit message after a successful run.
Core principles (always): follow skills/core-principles — subject states user impact concisely; no motivation paragraphs or padding.
Subject rules
- One line, ≤ 70 chars, user-impact framing — what changes for the user, not which files were touched
- Verb-first: "Add", "Fix", "Allow", "Reject", "Block"
- No file names in the subject: "Refactor auth.py" is bad; "Reject empty emails at signup" is good
- Match existing style: if the repo uses Conventional Commits (
type(scope): subject), keep that format; otherwise freeform- Detect Conventional Commits:
pyproject.tomlhas[tool.commitizen], or.cz.toml/commitlint.config.jsexists
- Detect Conventional Commits:
Bad → Good
| Bad | Good |
|---|---|
update auth.py and tests |
Reject empty emails before hashing |
fix bug |
Stop retry storm on 5xx from upstream |
address review comments |
Enforce non-empty email at signup |
Body rules
The body is for the future bisecting engineer, not the current reviewer:
- ≤ 3 sentences total, or equivalent compact bullets
- Cover only: what changed at the user-impact level, breaking-change pointers, irreplaceable invariants
- Cut: "why the problem existed", motivation paragraphs, "why we picked X over Y" — all of that belongs in the PR description
- If the subject is already complete and nothing durable remains to add, omit the body
Output format
<subject — one line, ≤70 chars, user-impact>
<body — ≤3 sentences; omit entirely if nothing durable to add>
Provide raw text to the caller — do not wrap in a code fence by default (breaks piping to git commit -F -).
When presenting to the user as a readable deliverable, wrap in a single fenced code block.
No git commit — ever
Agents never run git commit or git push. The skill produces text only.
Present the draft in a fenced code block so the user can copy it and run:
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 · 67 lines · 50 tokens per session scan A 40cacd7ca3f3
commit-message is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 626 once invoked, about $0.0003 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…