Borrowing it
Nothing to install: this file belongs to navraj007in/architecture-cowork-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.
curl -O https://raw.githubusercontent.com/navraj007in/architecture-cowork-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/navraj007in/architecture-cowork-pluginWrote 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.
[](https://agentmods.dev/instructions/navraj007in/architecture-cowork-plugin/agents-md)<a href="https://agentmods.dev/instructions/navraj007in/architecture-cowork-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/navraj007in/architecture-cowork-plugin/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.
<a href="https://agentmods.dev/instructions/navraj007in/architecture-cowork-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/navraj007in/architecture-cowork-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.06302 | $0.06302 |
| Opus 5.5 | $0.02521 | $0.02521 |
| Sonnet 5.5 | $0.01260 | $0.01260 |
| Haiku 4.5 | $0.00630 | $0.00630 |
Grade A, and why
architecture-cowork-plugin 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- architecture-cowork-plugin CLAUDE.md — 91% identical, 81 lines differ
How it starts
The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archon Plugin — Global Rules
These rules apply to ALL commands in this plugin.
Request Routing — When to Use Commands vs. Handle Directly
Only invoke a plugin command when the user explicitly uses /architect:<command> syntax.
For everything else, handle the request directly as a normal coding or software task:
| User says | Do this |
|---|---|
| "fix errors", "fix the build", "it's not compiling" | Read the error output, fix source files directly — do NOT run a command |
| "fix the TypeScript errors in X" | Edit the file and fix the types — do NOT run a command |
| "install dependencies" | Run the install command directly |
| "why is X failing?" | Investigate and explain directly |
| "update file X" | Edit the file directly |
| General coding questions | Answer directly |
Never route a free-form user message to /architect:blueprint or any other command unless the user explicitly asked for it.
The scaffold commands (/architect:scaffold, /architect:scaffold-component) already include a build + fix step. If the user asks to fix errors after scaffold, they want you to fix the code directly in the scaffolded directory — not re-run the scaffold or generate blueprints.
Output File Splitting
Generate architecture output in full detail — never be vague or truncate content.
When a deliverable is large, split it across multiple files rather than reducing detail:
| Deliverable | Split pattern |
|---|---|
data-model.md |
data-model-1.md, data-model-2.md, … (group by domain/module) |
security-architecture.md |
security-architecture-auth.md, security-architecture-network.md, … |
application-architecture.md |
application-architecture-backend.md, application-architecture-frontend.md, … |
sprint-backlog.md |
sprint-backlog-1.md, sprint-backlog-2.md, … (one file per sprint or sprint group) |
setup-env.md |
setup-env-services.md, setup-env-local.md, … |
| ORM schemas | schema-{domain}.prisma per domain (e.g. schema-auth.prisma, schema-orders.prisma) |
| Any other deliverable | {name}-{section}.md or {name}-{N}.md |
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.
- 1mo ago First seen · 500 lines · 6,302 tokens per session scan A 489f572435d2
architecture-cowork-plugin AGENTS.md is an instructions file published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 6,302 tokens to every session, about $0.0252 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.
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).
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.
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).
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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.