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 commands/anilcancakir/claude-code-plugin/commitgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginWhat 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 | $0.00021 | $0.02534 |
| Opus 5 | $0.00010 | $0.01267 |
| Sonnet 5 | $0.00004 | $0.00507 |
| Haiku 4.5 | $0.00002 | $0.00253 |
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.
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(orgit 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
--interactivefrom 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:
-
Detect
--interactiveflag in $ARGUMENTS (enables interactive mode). Strip it from $ARGUMENTS. -
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"
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.
- yesterday First seen · 268 lines · 21 tokens per session scan A b097efac2ea8
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.
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.
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…
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…
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…
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.
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…