agentmods.dev

claude-architect AGENTS.md

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 CodexOpenCode

19 4d ago A scan 4,099 tokens original MIT
View the source file PyModel/claude-architect
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/pymodel/claude-architect/agents-md
Clone the repo
git clone --depth 1 https://github.com/PyModel/claude-architect

Made for: Codex, OpenCode.

Per session 4,099 This file is loaded in full into every session.
When invoked 4,099 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.

ModelPer sessionOnce invoked
Fable 5 $0.04099 $0.04099
Opus 5 $0.02049 $0.02049
Sonnet 5 $0.00820 $0.00820
Haiku 4.5 $0.00410 $0.00410

Measured 2d ago against content hash eaaddb4206c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 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 · 236 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. 2d 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 (19 stars, last pushed 4d ago), licensed MIT. It adds 4,099 tokens to every session, about $0.0205 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 2026-08-30.

Building agentsclaude-codeclaude-code-plugincodexdelegationdeveloper-toolsopencode
Related

Other instructions, from other repositories

copilot-api AGENTS.md

Instructions for caozhiyuan/copilot-api, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

caozhiyuan/copilot-api · 652 tokens

opencode-ensemble AGENTS.md

AGENTS.md instructions for hueyexe/opencode-ensemble, covering opencode-ensemble — agent guidelines, what this is, design context, users and brand personality.

hueyexe/opencode-ensemble · 4,577 tokens

20x AGENTS.md

Instructions for peakflo/20x, covering agents.md — multi-agent architecture (implemented), agent model, database schema, architecture and adapter architecture.

peakflo/20x · 6,580 tokens

untether CLAUDE.md

Instructions for littlebearapps/untether, covering untether, features (vs upstream takopi), architecture, key files and reference docs.

littlebearapps/untether · 10,500 tokens

untether GEMINI.md

Instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.

littlebearapps/untether · 500 tokens

paseo AGENTS.md

AGENTS.md instructions for getpaseo/paseo, a project described as: Orchestrate multiple coding agents from desktop and mobile.

getpaseo/paseo · 4 tokens