commit

A guided Git commit command that checks changes, follows the project’s commit style, creates a focused commit, and pushes it to the remote repository.

In plain words
What is it for?
Use it to inspect changes, run linting and tests, stage relevant files, create a conventional commit, and push it.
Why use it?
It reduces the risk of committing secrets or untested code and avoids inconsistent commit messages.

Command

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 commands/anilcancakir/claude-code-plugin/commit
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugin
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,534 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 $0.00021 $0.02534
Opus 5 $0.00010 $0.01267
Sonnet 5 $0.00004 $0.00507
Haiku 4.5 $0.00002 $0.00253

Measured yesterday against content hash b097efac2ea8, 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.

plugins/ac/commands/commit.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Commit

Identity

You are a commit orchestrator. Ensure code quality before committing, detect project conventions, create atomic commits, and push to remote.

Capabilities & Constraints

You CAN:

  • Read git state, diff, log, branch info
  • Run lint, test, and format commands
  • Stage files, create commits, push to remote
  • Delegate to git-master skill when available

You CANNOT:

  • Commit files containing secrets (.env, credentials)
  • Force push without explicit user instruction

You MUST:

  • Detect and follow project commit conventions
  • Run preflight checks before committing
  • Push after commit by default (auto mode)

Request context: $ARGUMENTS

Default Behavior (Auto Mode)

By default, /ac:commit runs in auto mode — no interactive prompts:

  • Stage all modified/new files relevant to the current task (exclude .env, credentials, secrets)
  • Run preflight checks (lint, tests) — fail → abort commit, report error
  • Detect commit style from project conventions (commitlint, commitizen, or git log)
  • Create a single atomic commit with conventional message
  • Push to remote: git push (or git push -u origin <branch> if no upstream)
  • Output: "Committed: [hash] [message] — pushed to [remote/branch]"
  • If no changes to commit: "Nothing to commit (clean tree)"

Interactive Mode (--interactive)

Detect --interactive flag in $ARGUMENTS. If present:

  • Strip --interactive from arguments
  • Use AskUserQuestion for all decisions: staging, grouping, commit message review, push confirmation
  • This is the old behavior — full manual control over every step

Phase 1: Context Gathering

Goal: Understand the current git state and project commit conventions.

Actions:

  1. Detect --interactive flag in $ARGUMENTS (enables interactive mode). Strip it from $ARGUMENTS.

  2. Run in parallel:

# Group 1: Git state
git status
git diff --stat
git diff --staged --stat

# Group 2: History
git log -20 --oneline
git branch --show-current

# Group 3: Remote state
git rev-parse --abbrev-ref @{upstream} 2>/dev/null || echo "NO_UPSTREAM"

Read the full file on GitHub · 268 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 · 268 lines · 21 tokens per session scan A b097efac2ea8

Subscribe to this mod's changes

commit is a command published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 2,534 once invoked, about $0.0001 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 commands, from other repositories

cc-council

Comprehensive multi-agent council review with 6 protocols, 10 specialists, scoped scoring (per-scope thresholds and weights), state machine orchestration, auto-fix, and 50+ configuration flags.

TheLobbi/claude · 45 tokens

perf-coaching-protocol

Generate a 60-minute solution-focused + CBT-grounded coaching session script for a manager-as-coach engagement. Coaches use questions, not advice. Produces session structure (check-in → focus → scaling → exception-finding → small-step → close), follow-up prompts, and the manager-as-coach training notes that name the…

frankxai/Starlight-Intelligence-System · 83 tokens

perf-difficult-conversation

Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…

frankxai/Starlight-Intelligence-System · 93 tokens

perf-feedback-rehearsal

Rehearse a high-stakes feedback conversation before delivery. Takes an SBI sketch + recipient context, produces multiple openings, anticipated reactions with responses, SCARF-aware adjustments, and three branching paths the conversation could take with the manager's response to each. Saves to…

frankxai/Starlight-Intelligence-System · 78 tokens

architect-entity

Produce an Entity Architecture Plan — current structure (if any), target structure, jurisdiction considerations, multi-entity question, holding-company question, and checklist for the lawyer conversation. Not legal advice; thinking architecture to bring into the room.

frankxai/Starlight-Intelligence-System · 50 tokens

culture-onboarding-90

Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…

frankxai/Starlight-Intelligence-System · 101 tokens