auto-commit

An agent that groups, stages, and commits repository changes into separate atomic commits. Staging selects changes for a commit, and a repository is the project’s version-controlled file store.

In plain words
What is it for?
Use it to turn eligible current-project changes into logical commits with standard commit messages.
Why use it?
It organizes pending changes, avoids committing detected secrets, and leaves a clean working tree when possible.

Skill for Claude CodeCodex

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 skills/mystilleef/spae-framework/auto-commit
Any agent
npx skills add mystilleef/spae-framework --skill auto-commit
Clone the repo
git clone --depth 1 https://github.com/mystilleef/spae-framework

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,199 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00019 $0.01199
Opus 5 $0.00010 $0.00600
Sonnet 5 $0.00004 $0.00240
Haiku 4.5 $0.00002 $0.00120

Measured yesterday against content hash 92cd68752669, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

auto-commit scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- prettier-ignore-start -->
skills/auto-commit/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-commit agent

When to use

  • Invoke for any repository with pending changes that should land as atomic commits.
  • Execute immediately upon invocation. Never wait for user input or confirmation before git status.

Goal

  • Analyze repository changes, form safe atomic groups, block secrets, stage targeted files, and create conventional commits in the current project.
  • Commit all eligible current-project changes as separate, logical, atomic commits.
  • Leave the working tree clean unless safety checks or git errors block completion.

Input

Determine input from the current repository state:

  • Tracked, untracked, staged, unstaged, renamed, deleted, and ignored changes reported by git.
  • Atomic grouping heuristics from references/atomic-git-staging.md.
  • Commit message rules from references/conventional-commit.md.

Workflow

  1. GATE—Run git --no-pager status --porcelain=v2 --branch. Halt on no changes or git error.
  2. ORIENT—Goal: commit all eligible changes as atomic commits. Scope: current project. No changes outside git state.
  3. PLAN—Group files into logical commits. Isolate .gitignore changes. Apply fast path for a single unstaged file.
  4. ACT (repeat steps 4–6 per group until no eligible changes remain)
    • Scan candidate paths and content for secrets (pre-stage).
    • Run git --no-pager diff --no-ext-diff --stat --minimal --patience --histogram --find-renames --summary --no-color -U10 <file_group>.
    • Run git --no-pager add <file1> <file2> ....
    • Scan staged diff for secrets (pre-commit).
    • Generate conventional commit message.
  5. VERIFY—Confirm staged diff matches intent and all secret checks pass. On failure: unstage, halt, report.
  6. PERSIST—Run git --no-pager commit -m "<message>". Confirm commit success.
  7. REPORT—Emit the result following the result directives and using the result template.

Directives

  • Atomic Grouping: Commit files together only when they must change together, such as implementation plus matching tests.
  • Gitignore Isolation: Commit .gitignore changes separately.
  • Sensitive Path Rules: Hard-block .env* except .env.example, *.key, *.pem, *.p12, *.pfx, *_rsa, *_dsa, id_*, secrets.*, credentials.*, .aws/, .ssh/, and .gnupg/.

Read the full file on GitHub · 142 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 142 lines · 19 tokens per session scan C 92cd68752669

Subscribe to this mod's changes

auto-commit is a skill published in the GitHub repository mystilleef/spae-framework (1 stars, last pushed 28d ago), licensed MIT. It adds 19 tokens to every session and 1,199 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

exploit-xss

Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site scripting, script injection, or needs to test JavaScript injection in parameters, forms, headers, or DOM sources.

crazyMarky/pentest-skills · 71 tokens

results-storage

SQLite-based persistent storage and reporting system for penetration testing results. Use this skill when user needs to store scan results, query vulnerabilities, generate reports, or manage pentest data across sessions.

crazyMarky/pentest-skills · 40 tokens

exploit-sqli

SQL injection detection and exploitation using sqlmap, manual techniques, and custom payloads. Use this skill when user needs to test for SQL injection vulnerabilities, extract database information, or exploit SQLi in parameters, headers, or cookies.

crazyMarky/pentest-skills · 51 tokens

recon-dir-scan

Directory and file enumeration using ffuf, gobuster, dirsearch, and feroxbuster. Use this skill when user needs to discover hidden directories, enumerate files, find backup files, or map application structure through path fuzzing.

crazyMarky/pentest-skills · 52 tokens

recon-fingerprint

Web fingerprinting and WAF detection using wafw00f, whatweb, nuclei, and httpx. Use this skill when user needs to identify web technologies, detect WAF/CDN, analyze server headers, or fingerprint web applications and frameworks.

crazyMarky/pentest-skills · 55 tokens

recon-subdomain

Subdomain enumeration and DNS reconnaissance using subfinder, amass, dnsx, and other tools. Use this skill when user needs to discover subdomains, perform DNS enumeration, gather DNS records, or find hidden subdomains of a target domain.

crazyMarky/pentest-skills · 54 tokens