What is three-pillars-plugin CLAUDE.md?

Project instructions for a Claude Code plugin built around the Three Pillars framework for structured software development. The framework keeps living documents for the product vision, architecture, and roadmap.

It guides setup and development using project documentation, test-driven development, Claude Code skills, and the plugin’s required files and conventions.

It gives coding work a shared record of why the project exists, how it is built, and what should happen next, while connecting development practices to those decisions.

How CurtisThe/three-pillars-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CurtisThe/three-pillars-plugin. 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/CurtisThe/three-pillars-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/CurtisThe/three-pillars-plugin

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/curtisthe/three-pillars-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/curtisthe/three-pillars-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/curtisthe/three-pillars-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/curtisthe/three-pillars-plugin/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/curtisthe/three-pillars-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/curtisthe/three-pillars-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,828 This file is loaded in full into every session.

When invoked 2,828 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	$0.02828	$0.02828
Opus 5.5	$0.01131	$0.01131
Sonnet 5.5	$0.00566	$0.00566
Haiku 4.5	$0.00283	$0.00283

Measured 21d ago against content hash 1540945d1c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

three-pillars-plugin 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 21d 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ This file is generated — do not edit directly

This CLAUDE.md is shipped from a private dev repo via release.sh. Direct edits to this file (or any other file in this repo's allowlist: skills/, agents/, .claude-plugin/, settings.json, statusline.sh, LICENSE, CONTRIBUTING.md, etc.) will be overwritten on the next release.

To contribute: open an issue or PR describing the change. The maintainer will apply it upstream and re-release. See CONTRIBUTING.md.

Three Pillars Framework

This machine uses the three-pillars skill framework for structured software development with Claude Code.

Project Docs

Every project should maintain four living docs in three-pillars-docs/:

vision.md — Problem, users, principles, non-goals, success signals. Source of truth for why the project exists. Read first by every other TDD skill — it is the filter for what work matters and the tie-breaker when technical options are equivalent. Created by /tp-setup as its first conversational step.
architecture.md — System architecture, key decisions, constraints. Source of truth for how the system is built.
product_roadmap.md — Current state, design inventory, implementation sequence. Source of truth for what to build next. Links to vision.md rather than duplicating the why.
known_issues.md — Open bugs and limitations by severity. Source of truth for what's broken.

Use /tp-setup first to establish the vision. Then /tp-docs-init to scaffold architecture, roadmap, and known-issues from codebase analysis. Use /tp-docs-update to maintain them after milestones.

Getting Started

Fresh project setup follows a deliberate order — why before how, how before tests:

/tp-setup — Draws out the project's "why" into three-pillars-docs/vision.md (conversational). Vision only; no test-runner decisions here. Run first on any new project.
/tp-docs-init — Scaffolds architecture.md, product_roadmap.md, and known_issues.md from codebase analysis. Uses vision.md as context.
/tp-test-setup — Configures test infrastructure (test runner, layout, permissions, starter test). Runs after architecture so test-runner and layout choices are informed by the documented structure, not guessed at before.

Read the full file on GitHub · 160 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.

21d ago Changed · +8 lines · +386 tokens per session 1540945d1c5a
2mo ago First seen · 152 lines · 2,442 tokens per session scan A e80d1c5b005c

Subscribe to this mod's changes

three-pillars-plugin CLAUDE.md is an instructions file published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 11d ago), licensed Apache-2.0. It adds 2,828 tokens to every session, about $0.0113 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 2026-08-31.

Planning TDD

three-pillars-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
three-pillars-plugin CLAUDE.mdCurtisThe/three-pillars-plugin	Instructions file	4	11d ago	Apache-2.0	A	2,828	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

three-pillars-plugin: Instructions file for Claude Code