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/evolplus/talos/git-commitnpx skills add evolplus/talos --skill git-commitgit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00049 | $0.02629 |
| Opus 5 | $0.00024 | $0.01314 |
| Sonnet 5 | $0.00010 | $0.00526 |
| Haiku 4.5 | $0.00005 | $0.00263 |
Grade A, and why
git-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 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Discipline
When to use
Any time an agent (or human) is about to run git commit in a worktree or the main branch. Also at project setup, before the first commit, to verify identity and .gitignore. The skill applies cross-phase — BA's SRS edits, SA's architecture edits, Dev's code changes, DevOps's deploy scripts, non-SDLC agents' report files all flow through the same commit discipline.
agents: [all] is a sentinel — this skill is registered under Cross-cutting in .claude/skills/registry.md and applies to every agent in the kit.
Inputs and outputs
- Inputs: the change to commit; the master-plan task ID (
T-NNN) it serves if applicable; the agent role making the commit; for human-contributed work, the human's name + email - Outputs: a well-formed conventional commit in the current local worktree, with identity, traceability, and any required attribution trailers
Procedure
- Identity check (one-time per worktree). Run
git config user.email && git config user.name. If either returns empty, halt — do not commit. Tell the user to configure (see "Configuring identity" below). .gitignorecheck (one-time per repo). Verify the repo has a.gitignorecovering at minimum: env files, secrets, IDE artifacts, build outputs, OS files, the kit's own.tmpstaging files. Usereferences/gitignore-template.mdas the baseline.- Stage the changes.
git add <paths>— nevergit add .blindly. Verify withgit statusandgit diff --cachedbefore committing. - Compose the commit message per
references/conventional-commits-format.md:- Subject line:
<type>(<scope>): <description>— short, lowercase, no trailing period - Blank line, then body (optional but encouraged for non-trivial commits)
- Blank line, then footer trailers (task ref, attribution)
- Subject line:
- Verify message against the regex in
conventional-commits-format.md. If it doesn't match, rewrite — don't bypass with--no-verify. - Add the task reference. Every commit made for a master-plan task should reference that task (e.g.,
Refs: T-014in the footer, or scope-tagged likefeat(billing)(T-014): …). - Add attribution trailers where they apply (see
references/compliance-policy.md):Co-authored-by: <name> <email>when a human's contribution shaped this commit (notably thedesign-human-editedFigma flow per CLAUDE.md §4)Generated-By: <agent-role>when an agent (Claude Code instance) is the primary author
- Commit.
git commit -m "..."for single-line, orgit committo open the editor for multi-line. - Do not push or merge local worktree history. A sub-agent worktree under
.worktrees/<role>-<task-id>/is detached and local-only. Never rungit push,git pull,git merge,git rebase, orgit cherry-pickfrom it. The Orchestrator promotes validated file content to main by path-scoped ingestion per.claude/rules/worktree-isolation.md§5.
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.
- 2d ago First seen · 148 lines · 49 tokens per session scan A f0f39e6c59d6
git-commit is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,629 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…