git-perfectionist

git-perfectionist is an agent for Claude Code from povvo/claudikins-kernel. It costs 330 tokens per session (2,105 once invoked), scanned A, original, MIT.

A documentation agent that updates README files, changelogs, and version files to match shipped code.

In plain words
What is it for?
Use it during the shipping process to review and update one documentation section at a time, with human approval before each edit.
Why use it?
It reduces the risk that project documentation describes features or versions that were not actually released.

Agent for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claudikins-kernel plugin — 4 skills, 4 commands, 8 agents, 8 hooks shipped together

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 agents/povvo/claudikins-kernel/git-perfectionist
Clone the repo
git clone --depth 1 https://github.com/povvo/claudikins-kernel

Made for: Claude Code.

Or install claudikins-kernel, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 8 agents, 8 hooks.

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 git-perfectionist

README.md
[![agentmods](https://agentmods.dev/badge/agents/povvo/claudikins-kernel/git-perfectionist.svg)](https://agentmods.dev/agents/povvo/claudikins-kernel/git-perfectionist)
Your own site
<a href="https://agentmods.dev/agents/povvo/claudikins-kernel/git-perfectionist"><img src="https://agentmods.dev/badge/agents/povvo/claudikins-kernel/git-perfectionist.svg" alt="Measured on agentmods" height="20"></a>
Per session 330 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00330 $0.02105
Opus 5 $0.00165 $0.01052
Sonnet 5 $0.00066 $0.00421
Haiku 4.5 $0.00033 $0.00211

Measured 6d ago against content hash 8c587853ba87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

git-perfectionist 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 6d 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/git-perfectionist.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

git-perfectionist

You update documentation to match shipped code. GRFP-style: one section at a time, human approval for each.

"Docs are part of shipping. GRFP them." - Shipping philosophy

Core Principle

Section-by-section approval. Never batch documentation changes.

You're not here to auto-generate docs. You're here to draft, present, get approval, repeat.

What You DO

  • Read current documentation state
  • Identify gaps from recent changes
  • Draft updates ONE SECTION at a time
  • Present each section for human approval
  • Apply approved changes via Edit tool
  • Follow Keep a Changelog format

What You DON'T Do

  • Batch multiple sections without approval
  • Auto-apply changes without human review
  • Create new files (use Edit on existing)
  • Skip sections because "they're obvious"
  • Fabricate features or capabilities

Prerequisites

Before you run:

  1. /claudikins-kernel:verify must have PASSED - Code works
  2. Stage 2 (Commit Strategy) approved - Know what we're shipping
  3. Human initiated Stage 3 - Documentation phase started

If these aren't met, do not proceed.

The GRFP Process

One section at a time. Present. Approve. Edit. Repeat.

1. Read current docs
   └─► Identify what exists

2. Read ship-state.json
   └─► Understand what changed

3. Identify gaps
   └─► What docs need updating?

4. For each section:
   ├─► Draft the update
   ├─► Present to human
   ├─► Wait for approval
   └─► Apply via Edit tool

5. Repeat until all sections done

Files to Update

File What to Update Format
README.md Features, usage, installation Markdown
CHANGELOG.md New version entry Keep a Changelog
package.json / Cargo.toml / pyproject.toml Version bump Semver

Read the full file on GitHub · 333 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. 6d ago First seen · 333 lines · 330 tokens per session scan A 8c587853ba87

Subscribe to this mod's changes

git-perfectionist is an agent published in the GitHub repository povvo/claudikins-kernel (126 stars, last pushed 4mo ago), licensed MIT. It adds 330 tokens to every session and 2,105 once invoked, about $0.0016 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 2026-08-30.

Related

Other agents, from other repositories

CHANGELOG

Agent "CHANGELOG" from spencermarx/open-code-review, covering 2.5.0 (2026-07-28), 🩹 fixes, ❤️ thank you, 2.4.0 (2026-06-28) and 🚀 features.

spencermarx/open-code-review · 0 tokens

commit

Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).

fusengine/agents · 63 tokens

release-manager

Owns the release pipeline: certification checklists, store submissions, platform requirements, version numbering, and release-day coordination. Use for release planning, platform certification, store page preparation, or version management.

IdoCohen560/claude-unity-game-studio · 43 tokens

code-reviewer

Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).

fusengine/agents · 55 tokens

technical-writer

Use when: creating or improving technical documentation — API reference, user guides, tutorials, architecture docs. Do NOT use for: designing the API contract itself (use api-designer) or writing implementation code.

fusengine/agents · 45 tokens

security-reviewer

USE BEFORE committing security-sensitive changes (auth, crypto, routes, templates, secrets). Audits current diff for OWASP-Top-10 patterns + deps typosquatting. Read-only. Returns Critical / Important / Nice schema with file:line. Model review — not a Semgrep/CodeQL replacement.

Filip-Podstavec/claude-leverage · 67 tokens