What is project-architect CLAUDE.md?

A Claude Code project-planning instruction set for preparing a software project from initial assessment through a pre-development approval step. It adapts the questions and deliverables to four project sizes: S, M, L, and XL.

Use it with /project-architect to qualify a project, inspect existing technology, define requirements and UX, plan the technical architecture, and produce files such as CLAUDE.md and implementation-roadmap.md.

It organizes discovery, requirements, design, architecture, schedule, and budget before coding begins. This helps teams carry a consistent plan into implementation.

project-architect CLAUDE.md — Instructions file for coding agents by arnwaldn: A Claude Code project-planning instruction set for preparing

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 instructions/arnwaldn/project-architect/claude-md

Clone the repo

git clone --depth 1 https://github.com/arnwaldn/project-architect

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/arnwaldn/project-architect/claude-md.svg)](https://agentmods.dev/instructions/arnwaldn/project-architect/claude-md)

Your own site

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

Per session 818 This file is loaded in full into every session.

When invoked 818 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00818	$0.00818
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 3d ago against content hash 011e9be7b87b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-architect 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

project-architect — Plugin Claude Code

Plugin de préparation de projet de développement, de la qualification initiale à la gate pré-dev. Une seule commande /project-architect, workflow adaptatif S/M/L/XL.

Architecture

8 phases séquentielles :

QUALIFIER — Taille du projet (S/M/L/XL) et Go/No-Go
COMPRENDRE — Contexte, existant, contraintes
STRATÉGISER — Stratégie et positionnement
SPÉCIFIER — Cahier des charges fonctionnel
DESIGNER — Brief UX/UI et direction artistique (24 questions, 9 blocs)
ARCHITECTURER — Architecture technique
PLANIFIER — Planning et budget
VALIDER — Gate pré-dev et fichiers-pont (CLAUDE.md, implementation-roadmap.md)

Matrice adaptative : data/adaptation-matrix.json contrôle quelles questions et quels livrables s'appliquent selon la taille S/M/L/XL. Invariant à préserver : les items sont monotones (S <= M <= L <= XL) pour chaque phase.

Fichiers clés

Fichier	Rôle
`commands/project-architect.md`	Skill principal (854 lignes, 82 questions)
`data/adaptation-matrix.json`	Matrice phases x tailles (308 items)
`agents/discovery-auditor.md`	Audit de l'existant technique (sonnet)
`agents/spec-architect.md`	Cahier des charges (sonnet)
`agents/tech-architect.md`	Architecture technique (sonnet)
`agents/pre-dev-validator.md`	Validation pré-dev (haiku)
`templates/*.md`	Les 7 templates de livrables
`docs/referentiel-workflow.md`	Le référentiel en 14 phases dont les 8 phases sont tirées
`tools/*.py`	Échafaudage hors plugin : tests et générateurs

Conventions

Questions numérotées Q{phase}.{num} (ex. Q5.14), continues par phase — vérifié par le test T5
Noms de phases en français (QUALIFIER, COMPRENDRE, etc.)
Items de la matrice monotones : S <= M <= L <= XL — vérifié par T3
Templates avec placeholders {variable}, accolades équilibrées — vérifié par T8
Agents référencés par chemin relatif dans .claude-plugin/plugin.json
Français accentué dans tout ce qui est lu par un humain
Aucune dépendance externe : bibliothèque standard Python uniquement

Read the full file on GitHub · 70 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 · 70 lines · 818 tokens per session scan A 011e9be7b87b

Subscribe to this mod's changes

project-architect CLAUDE.md is an instructions file published in the GitHub repository arnwaldn/project-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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 2026-08-31.

Planning Project Management ai-agents claude-code claude-code-plugin francais software-architecture

vibe-garden CLAUDE.md

Instructions for rjroy/vibe-garden, covering claude.md, repository overview, repository structure, plugins and compass rose.

rjroy/vibe-garden · 705 tokens

sideboard CLAUDE.md

Instructions for mmyslin/sideboard: Sideboard's own roadmap lives in GitHub Issues (mmyslin/sideboard). The project is GitHub-only — there is no roadmap.json / local-file mode.

mmyslin/sideboard · 893 tokens

vibe-garden copilot-instructions.md

Instructions for rjroy/vibe-garden, covering copilot code review instructions, confidence threshold, response format, do not comment on and language semantics you frequently misread.

rjroy/vibe-garden · 476 tokens

recursive-spine CLAUDE.md

Claude Code instructions for slopstopper/recursive-spine, covering recursive-spine — rules codex, mission, house rules, tracking (recursive-spine convention) and ci gates.

slopstopper/recursive-spine · 575 tokens

river-review GEMINI.md

Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.

s977043/river-review · 318 tokens

ship-it open-pr.instructions.md

Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…

khrichtchatyi/ship-it · 84 tokens