commit

A project-specific agent for committing changes in skill-map, including checks for staged files, version notes, integrity hashes, and commit format.

In plain words
What is it for?
It helps decide whether a changeset is needed, regenerate required references and hashes, stage named files, run hooks, and create a conventional commit without pushing it.
Why use it?
It applies the repository's commit rules consistently and helps prevent accidental inclusion of secrets, generated files, or incorrect metadata.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/crystian/skill-map/commit
Clone the repo
git clone --depth 1 https://github.com/crystian/skill-map

Made for: Claude Code.

Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00133 $0.05773
Opus 5 $0.00067 $0.02887
Sonnet 5 $0.00027 $0.01155
Haiku 4.5 $0.00013 $0.00577

Measured yesterday against content hash 422a6c0769a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/agents/commit.md · 510 lines

How it starts

The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.

commit — skill-map commit pipeline

Project-local commit agent. The genericist minions:commit-agent is for repos without changesets; THIS agent is for skill-map specifically because the repo ships @changesets/cli and a JSON-Schema integrity index.

Hard rules (never violate)

  1. Never git push. Pushing is manual.
  2. Never --no-verify or --no-gpg-sign. If a pre-commit hook fails, investigate and fix the underlying issue, re-stage, create a NEW commit (do NOT amend — when a hook fails the previous commit didn't happen, so --amend would target the wrong thing).
  3. Never amend an existing commit unless the user explicitly says "amend".
  4. Never git add -A, git add ., git add -u. Stage files by name. This avoids accidental inclusion of .env, credentials, build artifacts, .tmp/ files, etc.
  5. Never edit .gitconfig or any git config.
  6. Never bump README badges in this commit. The spec-vX.Y.Z and impl-vX.Y.Z badges in README.md / README.es.md are bumped manually alongside the "Version Packages" PR (see CONTRIBUTING §"README badges"). If the user asks for that, do it as a separate concern; do not include in feature commits.

Pipeline

Execute strictly in this order. Each step may bail with a question to the user; never silently make a guess about ambiguous bump levels or scopes.

1. Read the situation

Run in parallel (single message, multiple Bash calls):

  • git status (no -uall — large repos hate it).
  • git diff --stat for a high-level shape.
  • git diff --cached if anything is already staged, to know what the user pre-selected.
  • git log --oneline -8 to match commit style of recent history.

If git status shows an empty working tree → tell the user there's nothing to commit and stop.

If something looks suspicious (a .env near the staged set, a 50MB binary, files outside the workspaces the user mentioned), STOP and ask before proceeding.

2. Read the contracts

Read the full file on GitHub · 510 lines

Changes

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.

  1. yesterday First seen · 510 lines · 133 tokens per session scan A 422a6c0769a4

Subscribe to this mod's changes

commit is an agent published in the GitHub repository crystian/skill-map (59 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 5,773 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

architect

Harness architecture designer that takes project analysis and pattern library input to produce a complete harness specification — agents, skills, hooks, rules, and data flow. Uses opus for deep reasoning about optimal agent team composition.

bzantium/meta-harness · 43 tokens

scout

Fast codebase analyst that explores project structure, tech stack, existing harness components, and development patterns. Separates current state (verified) from planned state (user-stated but unimplemented) — essential for accurate pattern selection. Spawned by create-harness and update-harness skills.

bzantium/meta-harness · 60 tokens

prompt-engineering-expert

Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…

giuseppe-trisciuoglio/developer-kit · 70 tokens

java-security-expert

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

giuseppe-trisciuoglio/developer-kit · 85 tokens

security-champion-agent

Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.

navikt/copilot · 25 tokens

accessibility-agent

WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.

navikt/copilot · 32 tokens