checkin-assistant

checkin-assistant is a skill for Claude Code, Codex from ValorVie/custom-skills. It costs 59 tokens per session (2,532 once invoked), scanned A, original, MIT.

A checklist for the steps before making a Git commit. It treats a commit as one complete, reversible unit of work that should leave the codebase working.

In plain words
What is it for?
Use it to verify builds, tests, coverage, coding standards, dependencies, and security before committing code.
Why use it?
It helps catch failed builds, broken tests, code-quality problems, hardcoded secrets, and security issues before changes are recorded.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Language**: English | [繁體中文](../../../locales/zh-TW/skills/claude-code/checkin-assistant/SKILL.md).

Good fit Use it to verify builds, tests, coverage, coding standards, dependencies, and security before committing code.

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/ValorVie/custom-skills
agentmods
npx agentmods add skills/valorvie/custom-skills/checkin-assistant

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 checkin-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/valorvie/custom-skills/checkin-assistant/github.svg)](https://agentmods.dev/skills/valorvie/custom-skills/checkin-assistant)
Your own site
<a href="https://agentmods.dev/skills/valorvie/custom-skills/checkin-assistant"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/checkin-assistant/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 checkin-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/valorvie/custom-skills/checkin-assistant"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/checkin-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,532 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 $0.00059 $0.02532
Opus 5 $0.00030 $0.01266
Sonnet 5 $0.00012 $0.00506
Haiku 4.5 $0.00006 $0.00253

Measured 9d ago against content hash f47a795f2a86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

checkin-assistant 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.

upstream/uds/backup/skills/checkin-assistant/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkin Assistant

Language: English | 繁體中文

Version: 1.0.0 Last Updated: 2026-01-12 Applicability: Claude Code Skills


Purpose

This skill guides developers through pre-commit quality gates, ensuring every commit maintains codebase stability and follows best practices.

Note: This skill focuses on when and how to commit. For code review during PR, see Code Review Assistant.


Quick Reference (YAML Compressed)

# === CORE PHILOSOPHY ===
every_commit_should:
  - "Be a complete logical unit of work"
  - "Leave codebase in working state"
  - "Be reversible without breaking functionality"
  - "Contain its own tests (for new features)"
  - "Be understandable to future developers"

# === MANDATORY CHECKLIST ===
checklist:
  build:
    - "Code compiles (zero errors)"
    - "Dependencies satisfied"
    verify: "Run build command, exit code 0"

  tests:
    - "All existing tests pass (100%)"
    - "New code has tests"
    - "Coverage not decreased"
    verify: "Run test suite, check coverage"

  quality:
    - "Follows coding standards"
    - "No code smells (methods≤50, nesting≤3, complexity≤10)"
    - "No hardcoded secrets"
    - "No security vulnerabilities"
    verify: "Run linter, security scanner"

  docs:
    - "API docs updated"
    - "README updated (if needed)"
    - "CHANGELOG updated (user-facing changes → [Unreleased])"

  workflow:
    - "Branch naming correct (feature/, fix/, docs/, chore/)"
    - "Commit message formatted (conventional commits)"
    - "Synced with target branch"

# === NEVER COMMIT WHEN ===
blockers:
  - "Build has errors"
  - "Tests are failing"
  - "Feature incomplete (would break functionality)"
  - "Contains WIP/TODO in critical logic"
  - "Contains debugging code (console.log, print)"
  - "Contains commented-out code blocks"

# === COMMIT TIMING ===
good_times:
  - completed_unit: "Feature fully implemented with tests"
  - bug_fixed: "Bug fixed with regression test"
  - independent_refactor: "Refactoring complete, all tests pass"
  - runnable_state: "Code compiles, app can run"

bad_times:
  - "Build failures"
  - "Test failures"
  - "Incomplete features"
  - "Experimental code with scattered TODOs"

# === GRANULARITY ===
ideal_commit:
  files: "1-10 (split if >10)"
  lines: "50-300"
  scope: "Single concern"

split_rules:
  combine: ["feature + its tests", "tightly related multi-file changes"]
  separate: ["Feature A + B", "refactor + new feature", "bugfix + incidental refactor"]

# === SPECIAL SCENARIOS ===
emergency_leave:
  recommended: "git stash save 'WIP: description'"
  alternative: "Create wip/ branch"
  prohibited: "Commit WIP directly on feature branch"

experimental:
  branch: "experiment/topic-name"
  rules: "Free commits (no strict format)"
  success: "Clean up, squash, merge to feature"
  failure: "Document lessons, delete branch"

hotfix:
  branch: "hotfix/issue-name from main"
  rules: "Minimize changes, only fix the problem"
  message: "fix(scope): [URGENT] description"

Read the full file on GitHub · 404 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 · 404 lines · 59 tokens per session scan A f47a795f2a86

Subscribe to this mod's changes

checkin-assistant is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 2,532 once invoked, about $0.0003 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 2026-09-03.