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/ragnarok22/agent-skills/write-conventional-commitnpx skills add ragnarok22/agent-skills --skill write-conventional-commitgit clone --depth 1 https://github.com/ragnarok22/agent-skillsWhat 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 | $0.00076 | $0.00881 |
| Opus 5 | $0.00038 | $0.00441 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
write-conventional-commit 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 3d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Conventional Commit
Generate and apply Conventional Commits that follow the 1.0.0 specification.
Workflow
Step 1: Inspect commit scope
Run from repository root:
git status --short
git diff --staged --name-only
git diff --name-only
Use staged changes when available. If nothing is staged and the user asked to commit now, stage intentionally relevant files first and state what was staged.
Step 2: Classify intent into commit type
Pick the best type from change intent, not from file extension.
Common types:
feat: add a user-facing featurefix: fix a bugrefactor: code change without new feature or bug fixperf: improve performancedocs: documentation onlytest: add/update testsbuild: build/dependency toolingci: CI/CD configurationchore: maintenance that does not fit aboverevert: revert a previous commit
If uncertain between feat and fix, prefer:
fixwhen correcting broken behaviorfeatwhen adding new behavior
Step 3: Choose optional scope
Scope is optional and should be short and stable.
Prefer one of:
- top-level package/app (
api,billing,auth) - subsystem (
migrations,deps,release) - user-visible surface (
checkout,search)
Avoid broad scopes like misc.
Step 4: Detect breaking changes
Mark breaking changes when diff indicates incompatible API/contract behavior.
Signals include:
- removed/renamed public endpoints, fields, events, CLI flags
- required inputs changed incompatibly
- output schema changed incompatibly
When breaking:
- Add
!after type or type+scope (feat!:orfeat(api)!:) - Add footer:
BREAKING CHANGE: <what changed and how to migrate>
Use both when possible for clarity.
Step 5: Compose message in spec format
Use this structure exactly:
<type>[optional scope][!]: <description>
[optional body]
[optional footer(s)]
Formatting rules:
- Header type must be lowercase noun.
- Put a colon and single space after header prefix.
- Keep description concise and specific.
- Put one blank line between header and body.
- Put one blank line between body and footers.
- Footer tokens follow git trailer style (
Token: value), except references may useToken #value. - Use
BREAKING CHANGE:as the canonical breaking footer token.
What ships with it
3 files 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.
- 3d ago First seen · 139 lines · 76 tokens per session scan A c49c6b45f451
write-conventional-commit is a skill published in the GitHub repository ragnarok22/agent-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 881 once invoked, about $0.0004 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
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
commits
Use this skill whenever the user asks to commit changes, write or fix a commit message, amend or rename a commit, or do a workflow that includes committing in the IntelliJ repository. This is a thin repo-specific overlay: use IntelliJ commit format, write full commit messages by default, and keep requested suffixes…
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…