engram: Command for Claude Code

.claude/commands/commit.md

commit is a command for Claude Code from toejough/engram. It costs 12 tokens per session (511 once invoked), scanned A, original, Apache-2.0.

A guided way to create one Git commit from the current code changes. Git is a tool that records versions of a codebase, and a commit is one saved set of changes.

In plain words
What is it for?
Use it to review the current branch and changes, stage specific files, and create a commit with a type, explanation, and AI-Used note.
Why use it?
It prevents unrelated files from being included and gives the commit a consistent message explaining the reason for the change.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

This is toejough/engram's own configuration. It tells Claude Code how to work on engram itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything engram configures →

Reuse

Borrowing it

Nothing to install: this file belongs to toejough/engram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/toejough/engram/main/.claude/commands/commit.md
Clone the repo
git clone --depth 1 https://github.com/toejough/engram

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for commit

README.md
[![agentmods](https://agentmods.dev/badge/commands/toejough/engram/commit/github.svg)](https://agentmods.dev/commands/toejough/engram/commit)
Your own site
<a href="https://agentmods.dev/commands/toejough/engram/commit"><img src="https://agentmods.dev/badge/commands/toejough/engram/commit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for commit

Your own site · 80×15
<a href="https://agentmods.dev/commands/toejough/engram/commit"><img src="https://agentmods.dev/badge/commands/toejough/engram/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.00511
Opus 5.5 $0.00005 $0.00204
Sonnet 5.5 $0.00002 $0.00102
Haiku 4.5 $0.00001 $0.00051

Measured 2mo ago against content hash a44cca854e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.claude/commands/commit.md · 60 lines

What it actually says

Context

  • Current git status: !git status
  • Current git diff (staged and unstaged changes): !git diff HEAD
  • Current branch: !git branch --show-current
  • Recent commits: !git log --oneline -10

Your task

Based on the above changes, create a single git commit. Follow these rules exactly:

Staging

  • Stage files relevant to the current change using specific file paths
  • Do NOT use git add -A or git add .
  • Do not stage unrelated files

Message format

<type>(scope): <description>

<why we made this commit. what is the motivation, what problem does it solve, how does it fit into the bigger
picture? What decisions were made that led to this commit? were any lessons learned that future developers should be
aware of? This section should provide context and rationale for the change, not just a summary of what was done.>

AI-Used: [claude]

Common types: feat, fix, refactor, test, docs, chore

TDD phases:

Phase Format
TDD Red test(scope): add tests for <feature>
TDD Green feat(scope): implement <feature>
TDD Refactor refactor(scope): <cleanup>

Rules

  1. Trailer is AI-Used: [claude] — NOT Co-Authored-By
  2. Never amend pushed commits — check git status for "ahead of" first
  3. First line under 72 chars — body wrapped at 72 chars
  4. Separate concerns — don't mix functional changes with lint/style fixes
  5. Use HEREDOC for the commit message:
    git commit -m "$(cat <<'EOF'
    <message here>
    
    AI-Used: [claude]
    EOF
    )"
    

Use the Bash tool to stage and create the commit. Do not use any other tools. Do not send any other text besides the Bash tool calls.

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. 2mo ago First seen · 60 lines · 12 tokens per session scan A a44cca854e52

Subscribe to this mod's changes

commit is a command published in the GitHub repository toejough/engram (10 stars, last pushed 13d ago), licensed Apache-2.0. It adds 12 tokens to every session and 511 once invoked, about $0.0000 per session on Opus 5.5. 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

commit compared with commands from other repositories

commit next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
committoejough/engramCommand1013d agoApache-2.0A12Claude Code
rem_helpopenonion/connectonionCommand1.5kyesterdayApache-2.0B0Claude Code
commitechoVic/blade-codeCommand18124d agoMITA8Claude Code
speckit.archiveopsmill/infrahub-mcpCommand10yesterdayApache-2.0A15Claude Code
Checkpoint Commitopsmill/infrahub-mcpCommand10yesterdayApache-2.0A11Claude Code
statusAbdoKnbGit/tauCommand424yesterdaynoneA0Claude Code
commitBigSweetPotatoStudio/HyperChatCommand7082mo agononeA0Claude Code