What is plan-build-run CLAUDE.md?

A set of instructions for Claude Code, an AI coding assistant, to follow in a repository. It describes the Plan-Build-Run workflow, its rules, commands, and project structure.

Planning, implementing, checking, and verifying repository changes through the project's /pbr commands and specialized subagents.

It gives development work a defined process and tracks work in files, helping address quality loss as an AI assistant's conversation becomes full.

How SienkLogic/plan-build-run configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SienkLogic/plan-build-run. 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/SienkLogic/plan-build-run/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SienkLogic/plan-build-run

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/sienklogic/plan-build-run/claude-md/github.svg)](https://agentmods.dev/instructions/sienklogic/plan-build-run/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sienklogic/plan-build-run/claude-md"><img src="https://agentmods.dev/badge/instructions/sienklogic/plan-build-run/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sienklogic/plan-build-run/claude-md"><img src="https://agentmods.dev/badge/instructions/sienklogic/plan-build-run/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,684 This file is loaded in full into every session.

When invoked 2,684 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	$0.02684	$0.02684
Opus 5.5	$0.01074	$0.01074
Sonnet 5.5	$0.00537	$0.00537
Haiku 4.5	$0.00268	$0.00268

Measured 2mo ago against content hash 6d2aeaf0b4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan-build-run 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 2mo 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 · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

Plan-Build-Run is a Claude Code plugin that provides a structured development workflow. It solves context rot — quality degradation as Claude's context window fills up — through disciplined subagent delegation, file-based state, and goal-backward verification. Users invoke /pbr:* slash commands (skills) that orchestrate specialized agents via Task().

Critical Rules

NEVER add AI co-author lines to git commits or PRs. No Co-Authored-By: Claude or similar. Only add co-author lines referencing actual human contributors.
NEVER inline agent definitions into skill prompts. Use subagent_type: "pbr:{name}" — Claude Code auto-loads agent definitions from agents/. Reading agent .md files wastes main context.
Always use PBR workflow commands (/pbr:* skills) for development work, not ad-hoc manual fixes. PBR skills enforce state tracking, verification, and artifact creation that manual edits skip. When hooks don't fire (e.g., direct file edits outside Claude Code), workflow integrity degrades silently.
Post-work checklist — before finishing any task or session, verify: (1) npm test passes, (2) no uncommitted changes (git status is clean), (3) file paths in artifacts are correct and files exist. This catches drift that accumulates during long sessions.

Commands

npm test                    # Run all Jest tests
npm run test:coverage       # Jest with coverage enforcement
npm run test:dashboard      # Vitest dashboard tests
npm run lint                # ESLint on hooks and tests
npm run build:hooks         # Bundle hooks for distribution
npm run sync:generate       # Generate derivative plugins
npm run sync:verify         # Verify derivative consistency
npm run dashboard           # Launch dashboard UI
npm run dashboard:install   # Install dashboard dependencies

Coverage thresholds (enforced in jest.config.cjs): 55% statements, 47% branches, 58% functions, 56% lines.

Read the full file on GitHub · 186 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.

2mo ago First seen · 186 lines · 2,684 tokens per session scan A 6d2aeaf0b4a4

Subscribe to this mod's changes

plan-build-run CLAUDE.md is an instructions file published in the GitHub repository SienkLogic/plan-build-run (18 stars, last pushed 7mo ago), licensed MIT. It adds 2,684 tokens to every session, about $0.0107 per session on Opus 5.5. 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.

Planning agent-orchestration agentic-coding ai-coding ai-development anthropic claude

plan-build-run CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plan-build-run CLAUDE.mdSienkLogic/plan-build-run	Instructions file	18	7mo ago	MIT	A	2,684	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

plan-build-run: Instructions file for Claude Code