autonomous-ai-agency: Skill for Claude Code

.agents/skills/smart-commit/SKILL.md

smart-commit is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 34 tokens per session (787 once invoked), scanned A, original, MIT.

A commit checklist that runs tests and basic code and secret checks before creating a commit with a standard message format. A commit is a saved set of project changes in version control.

In plain words
What is it for?
Use it whenever code is ready to commit so the project passes its required checks and only explicitly chosen files are staged.
Why use it?
It catches failing tests, syntax problems, missing changelog updates, and accidentally staged secrets before changes are saved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

This is strikersam/autonomous-ai-agency's own configuration. It tells Claude Code and Codex how to work on autonomous-ai-agency 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 autonomous-ai-agency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to strikersam/autonomous-ai-agency. 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/strikersam/autonomous-ai-agency/master/.agents/skills/smart-commit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code, Codex.

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 smart-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/smart-commit/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/smart-commit)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/smart-commit"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/smart-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 smart-commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/smart-commit"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/smart-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00034 $0.00787
Opus 5 $0.00017 $0.00394
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00003 $0.00079

Measured 9d ago against content hash ac0502d8ab74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

smart-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 9d 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/skills/smart-commit/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: smart-commit

When to Use

Use this skill every time you are ready to commit code. It replaces ad-hoc git add && git commit with a structured quality gate sequence.


Instructions

Step 1 — Confirm changelog is updated

git diff docs/changelog.md

If the diff is empty and this is a code change (not chore/test/docs), update docs/changelog.md under ## [Unreleased] before continuing.

Step 2 — Run tests

pytest -x

Block on failure. Do not commit with failing tests. Fix the failure first.

Step 3 — Check for obvious issues

# Syntax check staged Python files
git diff --staged --name-only | grep '\.py$' | xargs python -m py_compile

# Confirm no secrets in staged files
git diff --staged | grep -iE '(SECRET_KEY\s*=\s*["\x27][^"\x27]{8}|password\s*=\s*["\x27][^"\x27]{4}|api_key\s*=\s*["\x27]sk-)'

If any secrets are detected: stop immediately, do not commit.

Step 4 — Stage your changes

git status                          # review what changed
git diff --staged                   # confirm what's staged
git add <specific files>            # stage by name, not -A

Step 5 — Write a conventional commit message

Format: <type>(<scope>): <short description>

Type When to Use
feat New feature visible to users
fix Bug fix
refactor Code change with no behaviour change
test Adding or updating tests
docs Documentation only
chore Tooling, config, dependencies
ci CI/CD changes
style Formatting, whitespace (no logic change)
perf Performance improvement
security Security fix or hardening

Examples:

feat(router): add task classification for long-context requests
fix(auth): reject tokens with empty bearer string
refactor(agent): extract planner prompt into prompts.py
security(key_store): hash keys before comparison

Step 6 — Commit

git commit -m "$(cat <<'EOF'
feat(scope): description here

- Additional context if needed
- Reference issue if applicable

https://claude.ai/code/session_<id>
EOF
)"

Read the full file on GitHub · 122 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. 9d ago First seen · 122 lines · 34 tokens per session scan A ac0502d8ab74

Subscribe to this mod's changes

smart-commit is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 787 once invoked, about $0.0002 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.