What is claude-pilot CLAUDE.md?

A set of instructions for configuring and using the Claude Pilot plugin, including planning, test-driven development, and review workflows. Test-driven development means writing tests before the code they check.

Use it to set up the plugin and follow its documented planning, execution, testing, and review commands.

It gives coding agents a consistent process for planning, implementing, and reviewing changes.

How changoo89/claude-pilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to changoo89/claude-pilot. 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/changoo89/claude-pilot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/changoo89/claude-pilot

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/changoo89/claude-pilot/claude-md.svg)](https://agentmods.dev/instructions/changoo89/claude-pilot/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/changoo89/claude-pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/changoo89/claude-pilot/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,106 This file is loaded in full into every session.

When invoked 2,106 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02106	$0.02106
Opus 5	$0.01053	$0.01053
Sonnet 5	$0.00421	$0.00421
Haiku 4.5	$0.00211	$0.00211

Measured 3d ago against content hash 65be1cff1b1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-pilot CLAUDE.md 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 3d 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.

CLAUDE.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-pilot - Plugin Documentation

Version: 4.4.54 | Last Updated: 2026-02-08

⚠️ CRITICAL: Required Reference Documents

Before starting any work, you MUST read the following documents:

@docs/ai-context/project-structure.md - Project structure, tech stack, file tree
@docs/ai-context/docs-overview.md - Documentation architecture, Tier mapping, component references

These two documents are Tier 1 documents that all AI agents MUST reference before starting any work, along with CLAUDE.md.

Quick Start

/plugin marketplace add changoo89/claude-pilot#release
/plugin install claude-pilot
/pilot:setup

Plugin Architecture

Pure Plugin: No Python dependency, native Claude Code integration

Superpowers-Style Commands: All commands invoke skills (single source of truth)

Commands: ~10 lines (frontmatter + skill invocation)
Skills: All execution logic (steps, bash scripts, verification)
Pattern: Invoke the [skill-name] skill and follow it exactly

Core Features:

SPEC-First Planning: /00_plan "task"
TDD + Ralph Loop: /02_execute - Autonomous iteration until quality gates pass
Multi-Angle Review: /review - Parallel verification
Auto-Documentation: /document - 3-Tier sync

Workflow: Plan (/00_plan) → Confirm (/01_confirm) → Execute (/02_execute) → Review (/review) → Document (/document) → Close (/03_close)

OOM Optimization (v4.4.43)

Reduced Agent Calls: /03_close now uses 2 agents instead of 3 (33% reduction)
Merged Verification: Documentation sync and verification combined in single agent call
No External Dependencies: Pure bash link checking (removed npx markdown-link-check)
Streamlined Steps: 9 steps → 5 steps (44% reduction)

E2E Verification Framework (v4.4.43)

Mandatory Verification: Added Step 5 to /02_execute for actual functionality validation
Project Type Detection: Auto-detect web/CLI/library projects for appropriate verification
Chrome in Claude Integration: MCP tools for web project visual/functional testing
Retry Loop Pattern: Max 3 attempts with GPT Architect escalation on persistent failures
Graceful Fallback: Skip browser tests with warning when Chrome extension unavailable

Read the full file on GitHub · 201 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.

3d ago First seen · 201 lines · 2,106 tokens per session scan A 65be1cff1b1f

Subscribe to this mod's changes

claude-pilot CLAUDE.md is an instructions file published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 7mo ago), licensed MIT. It adds 2,106 tokens to every session, about $0.0105 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.

Building agents Claude Code agents ai-assistant claude-ai cli-tool

arm_1a2b_k1l2_cleanCode_avoidDuplication

Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.

colchuck-ai/ai-resource-manager · 248 tokens

arm_1a2b_7g8h_cleanCode_avoidComments

Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.

colchuck-ai/ai-resource-manager · 231 tokens

ai-resource-manager arm_index.instructions.md

Instructions for colchuck-ai/ai-resource-manager, covering arm rulesets, priority rules, installed rulesets and sample-registry/[email protected].

colchuck-ai/ai-resource-manager · 238 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-pilot: Instructions file for Claude Code