agentmods.dev

claude-architect: Instructions file for Claude Code

AGENTS.md

claude-architect AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from PyModel/claude-architect. It costs 4,416 tokens per session, scanned A, original, MIT.

Project instructions for a plugin that lets Claude Code delegate coding tasks to other coding agents in isolated Git worktrees. A worktree is a separate working folder for a Git branch.

In plain words
What is it for?
Use it to create delegation specifications, launch supported coding agents, supervise their processes, recover from crashes, and review candidate changes.
Why use it?
It separates generated work from the main project, verifies the result independently, and leaves a precise artifact for human review before integration.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions subagents; mentions Claude Code.

This is PyModel/claude-architect's own configuration. It tells Claude Code, Codex and OpenCode how to work on claude-architect itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-architect configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 32repo changed 13d ago A scan 4,416 tokens original MIT
View source ↗ PyModel/claude-architect
Reuse

Borrowing it

Nothing to install: this file belongs to PyModel/claude-architect. 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/PyModel/claude-architect/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/PyModel/claude-architect

Made for: Claude Code, Codex, OpenCode.

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 claude-architect AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pymodel/claude-architect/agents-md/github.svg)](https://agentmods.dev/instructions/pymodel/claude-architect/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pymodel/claude-architect/agents-md"><img src="https://agentmods.dev/badge/instructions/pymodel/claude-architect/agents-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.

agentmods 80×15 button for claude-architect AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pymodel/claude-architect/agents-md"><img src="https://agentmods.dev/badge/instructions/pymodel/claude-architect/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,416 This file is loaded in full into every session.
When invoked 4,416 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04416 $0.04416
Opus 5.5 $0.01766 $0.01766
Sonnet 5.5 $0.00883 $0.00883
Haiku 4.5 $0.00442 $0.00442

Measured 13d ago against content hash 8c5c5e1473bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-architect AGENTS.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 13d 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.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

Project purpose

Claude Architect is a cross-platform Claude Code plugin for verified delegation to Codex, OpenCode, Pi, and Pythinker. Claude authors a versioned Delegation Spec; the runtime launches an untrusted Producer in an isolated Git worktree, freezes its output as a Candidate Artifact, independently verifies it, and exposes the exact artifact for review and human-controlled integration.

The repository also contains a strictly non-mutating advisor, cross-platform process supervision, crash recovery, bounded redacted logging, and Producer capability routing.

Sources of truth

When sources disagree, use this descending precedence:

  1. JSON schemas in runtime/schemas/ and protocol constants in src/protocol/.
  2. Runtime behavior in src/; generated packaged output lives in runtime/.
  3. Contract and adversarial tests in tests/.
  4. The delegation workflow in skills/delegate/SKILL.md and role definitions in agents/.
  5. Plugin manifests in .claude-plugin/ and user-facing documentation.

When prose conflicts with an executable contract, correct the prose or explicitly migrate the contract. Never leave them silently inconsistent.

Mandatory operating rules

Code discovery

This repository is indexed by the codebase-memory-mcp server as project Users-panda-Projects-active-claude-architect.

  • For code exploration, use graph tools first: search_graph for symbols, get_code_snippet for exact source, trace_path for call chains, search_code for graph-assisted text search, and get_architecture for structure.
  • If the server or a required graph tool is unavailable, state that limitation, then fall back to repository search and direct file reads. Do not continue silently.
  • If the index is stale after substantial changes, run index_repository before relying on it.

Planning and approval

Before making a non-trivial change:

  • Read the relevant schema, implementation, tests, skill text, and recent Git history.
  • Inspect tasks/lessons.md and any active tasks/todo.md when present.
  • State the intended outcome, authorized scope, and verification method.
  • Inspect Git status and preserve unrelated user changes; never assume a dirty worktree is disposable.
  • Identify implications for macOS, Linux, Windows, and each affected Producer.

Read the full file on GitHub · 240 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. 13d ago Changed · +17 tokens per session 8c5c5e1473bd
  2. 14d ago Changed · +4 lines · +71 tokens per session 38d51b7072f0
  3. 1mo ago Changed · +229 tokens per session 2326cda9c115
  4. 1mo ago First seen · 236 lines · 4,099 tokens per session scan A eaaddb4206c0

Subscribe to this mod's changes

claude-architect AGENTS.md is an instructions file published in the GitHub repository PyModel/claude-architect (32 stars, last pushed 2d ago), licensed MIT. It adds 4,416 tokens to every session, about $0.0177 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.

Building agentsClaude Codeclaude-code-plugincodexdelegationdeveloper-toolsopencode
Related

Other instructions, from other repositories

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 · 9,715 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 · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens