agentmods.dev

commit-repo

commit-repo is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 41 tokens per session (1,281 once invoked), scanned B, original, MIT.

A guided skill for committing changes to repositories managed by Praxis. It determines the repository, reviews what is staged, proposes a commit message, and can require approval before committing.

In plain words
What is it for?
Use it to commit staged changes, optionally stage all changes, and commit automatically when the approval option is supplied.
Why use it?
It reduces mistakes when selecting files and writing commit messages, while keeping a human approval step by default.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/mat/dev/nano-vc.

Part of the dstoic plugin — 14 skills shipped together

not rated 20repo 4d ago B scan 41 tokens original MIT

Good fit Use it to commit staged changes, optionally stage all changes, and commit automatically when the approval option is supplied.

Compare 6 skills from other repositories ↓
View source ↗ digital-stoic-org/agent-skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add digital-stoic-org/agent-skills
Claude Code
/plugin install dstoic

Made for: Claude Code.

Or install dstoic, the plugin that ships this one along with the rest of its 14 skills.

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-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/commit-repo.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/commit-repo)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/commit-repo"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/commit-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00041 $0.01281
Opus 5 $0.00020 $0.00641
Sonnet 5 $0.00008 $0.00256
Haiku 4.5 $0.00004 $0.00128

Measured 7d ago against content hash a3499be70952, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

commit-repo scanned grade B 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add auto-approve rules for read-only git commands on each repo path. Example for `~/.claude/settings.json`:
dstoic/skills/commit-repo/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Repo

Streamlined commit flow for praxis-managed repos. One human gate only.

Repo Resolution

Resolve <repo-alias> to a git-managed path:

  1. If alias is the project root name (e.g., praxis): use CWD (the project root itself)
  2. Otherwise: look up alias in CLAUDE.md → Alias Paths section, extract the data path

Example CLAUDE.md format:

## Alias Paths

- **nano-vc**: control `$PRAXIS_DIR/repos/nano-vc` | data `/home/mat/dev/nano-vc`
- **agent-skills**: control `$PRAXIS_DIR/repos/agent-skills` | data `/home/mat/dev/agent-skills`

The data value = the git repo path to commit in.

If alias not found, list available aliases from CLAUDE.md and exit.

Arguments

  • $ARGUMENTS first word = repo alias (required)
  • --all flag: stage all modified files before committing (runs git add -A)
  • --yes flag: skip human confirmation gate — auto-approve the commit proposal
  • Without --all: only commits what's already staged

Flow

CRITICAL: Each git command MUST be a separate Bash call. NEVER chain with &&, ||, or ;. This enables auto-approval via permission rules.

Phase 1: Recon (auto-approved, no human gate)

Run these as separate sequential Bash calls:

  1. git -C <data-path> status
  2. git -C <data-path> diff --staged (if no --all flag) OR git -C <data-path> diff (if --all flag, to show what will be staged)
  3. git -C <data-path> log --oneline -5

Phase 2: Analyze + Propose

From the recon output:

  1. List files that will be committed (staged files, or all modified if --all)
  2. Determine conventional commit type(scope): description per CLAUDE.md rules
  3. Draft commit body: What: bullets + Why: line

Phase 3: Propose + Confirm + Execute

  1. Output the proposal as text:
---
📦 Commit proposal for <alias> (<branch>)

Staged files:
- file1
- file2

Commit message:
type(scope): description

What:
- change 1
- change 2

Why: reason
  1. If --yes flag is set: skip confirmation, proceed directly to step 3. Otherwise — ⚠️ MANDATORY HUMAN GATE — use AskUserQuestion:
    • Question: "Proceed with commit? (y/n/edit)"
    • If answer is empty/blank (known bug outside Plan Mode): fall back to inline text — output "Reply y to commit, n to abort, or edit to modify" and WAIT for user text reply
    • If "n" or denied: abort, report "❌ Commit aborted"
    • If "edit": ask what to change, revise, re-propose
    • If "y" or approved: proceed to step 3

Read the full file on GitHub · 149 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. 7d ago First seen · 149 lines · 41 tokens per session scan B a3499be70952

Subscribe to this mod's changes

commit-repo is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 1,281 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CommitsGit and workflow
Related

Other skills, from other repositories

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens

strict-tdd

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

a5c-ai/babysitter · 34 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…

redai-infra/Relax · 73 tokens