commit

commit is a skill for Claude Code from markmhendrickson/ateles. It costs 24 tokens per session (5,457 once invoked), scanned A, a copy of commit, MIT.

A commit workflow for Git repositories and submodules. It uses structured commit messages and includes tests and a security audit before staging changes.

In plain words
What is it for?
Committing the main repository, committing submodules, running tests, auditing files, and staging changes when checks pass.
Why use it?
It helps check changes and security requirements before creating a commit, including when a project contains nested repositories.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./foundation/security/pre-commit-audit.sh.

Good fit Committing the main repository, committing submodules, running tests, auditing files, and staging changes when checks pass.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles
agentmods
npx agentmods add skills/markmhendrickson/ateles/commit

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/skills/markmhendrickson/ateles/commit/github.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/commit)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/commit"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/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/skills/markmhendrickson/ateles/commit"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,457 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 91% copy Near-identical to another mod 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 $0.00024 $0.05457
Opus 5.5 $0.00010 $0.02183
Sonnet 5.5 $0.00005 $0.01091
Haiku 4.5 $0.00002 $0.00546

Measured 1mo ago against content hash 13f66fa1f951, 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 1mo 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.

Origin

This is a copy

91% identical to commit — 289 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/commit/SKILL.md · 515 lines

How it starts

The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Main Repository Commit Workflow

Run when:

  • No parameter provided (after committing all submodules)
  • "repo" parameter provided (skip submodules)

Ensure in root directory:

cd "$(git rev-parse --show-toplevel)"

Run entire test suite and resolve any errors as necessary. Proceed to analyze all uncommitted files for security vulnerabilities and patch as necessary.

CRITICAL: PRE-COMMIT SECURITY AUDIT - MUST RUN BEFORE STAGING:

Execute security audit from foundation/agent_instructions/cursor_rules/security.md (or .cursor/rules/foundation_security.md if installed) before staging ANY files:

  1. Run security audit script:

    # Use foundation security audit script if available
    if [ -f "foundation/security/pre-commit-audit.sh" ]; then
      ./foundation/security/pre-commit-audit.sh
    elif [ -f ".cursor/rules/foundation_security.md" ]; then
      # Follow security rule checks
      # (Implementation depends on how security rules are executed)
    fi
    
  2. If any check fails, ABORT immediately and alert the user. DO NOT proceed with staging or commit.

After security audit passes, proceed with:

NESTED GIT REPOSITORY DETECTION AND COMMIT (Optional, configurable):

Configuration: Enable/disable nested repo handling in foundation-config.yaml:

development:
  commit:
    handle_nested_repos: false  # Set to true to enable nested repo handling

If enabled, before committing the main repository, detect and commit any nested git repositories:

Nested repositories must be committed BEFORE the main repository to maintain consistency.

  1. Detect nested git repositories:

    # Find all nested .git directories (excluding the root .git and submodules)
    # Store in a temporary file to avoid subshell issues
    NESTED_REPOS_FILE=$(mktemp)
    find . -name ".git" -type d -not -path "./.git" -not -path "./.git/*" 2>/dev/null | sed 's|/.git$||' | sort > "$NESTED_REPOS_FILE"
    
    if [ -s "$NESTED_REPOS_FILE" ]; then
      echo "📦 Found nested git repositories:"
      while IFS= read -r repo_path; do
        echo "  - $repo_path"
      done < "$NESTED_REPOS_FILE"
      echo ""
    fi
    
  2. For each nested repository, commit changes:

    # Process each nested repo
    if [ -s "$NESTED_REPOS_FILE" ]; then
      while IFS= read -r repo_path; do
        if [ -n "$repo_path" ] && [ -d "$repo_path/.git" ]; then
          echo "🔄 Processing nested repository: $repo_path"
    
          # Save current directory
          ORIGINAL_DIR=$(pwd)
    
          # Change to nested repo directory
          cd "$repo_path" || {
            echo "  ❌ Failed to change to directory: $repo_path"
            rm -f "$NESTED_REPOS_FILE"
            exit 1
          }
    
          # Check if there are any changes
          if git status --porcelain | grep -q .; then
            echo "  📝 Found changes, committing..."
    
            # Run security audit for nested repo (same checks as main repo)
            echo "  🔒 Running security audit..."
            # (Run same security audit as main repo)
    
            # Stage all changes
            echo "  📝 Staging changes..."
            git add -A
    
            # Generate commit message for nested repo
            echo "  📝 Generating commit message..."
            # (Use configured commit message format)
    
            # Commit nested repo
            echo "  💾 Committing changes..."
            git commit -m "$COMMIT_MSG" || {
              echo "  ❌ Failed to commit nested repository: $repo_path"
              cd "$ORIGINAL_DIR"
              rm -f "$NESTED_REPOS_FILE"
              exit 1
            }
    
            # Push nested repo (if remote exists); reconcile and retry if rejected
            if git remote | grep -q .; then
              echo "  📤 Pushing to remote..."
              git push || {
                echo "  📥 Push rejected: reconciling with remote..."
                BRANCH=$(git branch --show-current)
                git pull --rebase origin "$BRANCH"
                git push || {
                  echo "  ⚠️  Warning: Failed to push nested repository: $repo_path"
                  echo "  Continuing with main repository commit..."
                }
              }
            else
              echo "  ℹ️  No remote configured, skipping push"
            fi
    
            echo "  ✓ Successfully committed nested repository: $repo_path"
          else
            echo "  ✓ No changes in $repo_path"
          fi
    
          # Return to original directory
          cd "$ORIGINAL_DIR" || {
            rm -f "$NESTED_REPOS_FILE"
            exit 1
          }
          echo ""
        fi
      done < "$NESTED_REPOS_FILE"
    
      # Clean up temp file
      rm -f "$NESTED_REPOS_FILE"
    fi
    

Read the full file on GitHub · 515 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. 1mo ago First seen · 515 lines · 24 tokens per session scan A 13f66fa1f951

Subscribe to this mod's changes

commit is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 5,457 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to commit, differing in 289 lines, and is treated as a copy.