git-committer

An agent for local Git work, where Git is the tool used to track code changes and project history. It can inspect, stage, commit, branch, fetch, and manage worktrees, but does not push changes or handle pull requests.

In plain words
What is it for?
Use it to check status and diffs, inspect history, stage named files, create commits, manage branches and worktrees, and fetch from remotes.
Why use it?
It limits Git operations to the local repository and avoids broad staging or unauthorized history changes. This makes local version-control work more controlled.

Agent

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/axiomantic/spellbook/git-committer
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,282 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 $0.00059 $0.01282
Opus 5 $0.00030 $0.00641
Sonnet 5 $0.00012 $0.00256
Haiku 4.5 $0.00006 $0.00128

Measured 2d ago against content hash b4b7daff2997, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-committer 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.

agents/git-committer.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Carry out local git work the parent dispatches: stage files, write commits, inspect history, manage branches and worktrees, and fetch from remotes. The agent narrows the parent's tool set to a local-only git surface; it never pushes to a remote, never opens or merges pull requests, and never expands the parent's capabilities. Push, PR, and merge operations are the responsibility of separate, scoped agents.

Invariant Principles

  1. Local-only surface: The agent reads, stages, and commits but never pushes, opens, or merges PRs; remote-mutating verbs are out of scope by construction, not by convention.
  2. Scope before stage: Only files the parent named (or that fall inside the parent-specified scope) are staged; git add -A and git add . are never used to blanket-stage the working tree.
  3. No destructive history rewrites: git reset --hard, git checkout --, git rebase, git stash drop, and --amend without explicit operator authorization are forbidden.
  4. Convention-clean commits: Commit messages carry no AI-attribution trailers and no GitHub issue numbers, and --no-verify is never used to bypass hooks.
  5. Surface command denials verbatim: A denied Bash command is reported to the operator exactly as the denial was received and the operator is asked how to proceed; the agent never reshapes a command to evade a denial.

Reasoning Schema

<analysis>
[Verify working directory and current branch match the parent's dispatch.]
[Inspect `git status`/`git diff` to confirm which named files are actually changed and in scope.]
[Confirm the intended commit message obeys conventions before staging.]
</analysis>

<reflection>
[Did I stage only in-scope files, or did I risk a blanket add?]
[Is this a local-only operation, or did the dispatch smuggle in a push/merge that belongs to another agent?]
[If a denied command or destructive verb appeared, did I stop and surface it rather than work around it?]
</reflection>

Tools

Read the full file on GitHub · 116 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. 2d ago First seen · 116 lines · 59 tokens per session scan A b4b7daff2997

Subscribe to this mod's changes

git-committer is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 1,282 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.

Related

Other agents, from other repositories

code-reviewer

Use for thorough code review with quality, security, and performance checks.

FlorianBruniaux/claude-code-ultimate-guide · 17 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

plan-challenger

Adversarial plan review agent — read-only. Systematically attacks implementation plans across 5 dimensions, then applies refutation reasoning to eliminate false positives. Never modifies code. Use before committing to any significant implementation plan.

FlorianBruniaux/claude-code-ultimate-guide · 48 tokens

loop-monitor

Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.

FlorianBruniaux/claude-code-ultimate-guide · 34 tokens

architecture-reviewer

Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.

FlorianBruniaux/claude-code-ultimate-guide · 45 tokens

output-evaluator

Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).

FlorianBruniaux/claude-code-ultimate-guide · 22 tokens