What is architext AGENTS.md?

Repository instructions for Architext, a tool for documenting software architecture and maintaining its generated guidance files.

They are for working on Architext's Rust CLI, architecture documentation, instruction rules, and synchronization process.

They explain which sections are managed automatically and which files developers should edit, reducing the risk of overwriting generated content.

How robot-accomplice/architext configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to robot-accomplice/architext. 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/robot-accomplice/architext/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/robot-accomplice/architext

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/robot-accomplice/architext/agents-md/github.svg)](https://agentmods.dev/instructions/robot-accomplice/architext/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/robot-accomplice/architext/agents-md"><img src="https://agentmods.dev/badge/instructions/robot-accomplice/architext/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/robot-accomplice/architext/agents-md"><img src="https://agentmods.dev/badge/instructions/robot-accomplice/architext/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,926 This file is loaded in full into every session.

When invoked 3,926 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	$0.03926	$0.03926
Opus 5.5	$0.01570	$0.01570
Sonnet 5.5	$0.00785	$0.00785
Haiku 4.5	$0.00393	$0.00393

Measured 2mo ago against content hash cf51c661f4e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architext 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

architext CLAUDE.md — 100% identical, 0 lines differ

AGENTS.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI assistants working on the Architext tool itself (this repository). For working on architecture data inside another repo that uses Architext, the Architext Architecture Documentation section at the bottom of this file is the project-consumer contract.

[!IMPORTANT] Two things in this file are managed by architext itself — keep all hand-written contributor guidance written as prose and tables, not bulleted lists, and leave the managed sections alone:

The Architext Architecture Documentation section (the ## heading near the end of this file) is upserted by architext sync (crates/architext-cli/src/commands/sync/instruction_files.rs); it replaces everything from that ## heading to the next ## heading. Edit the APPENDIX const in that file and viewer/AGENTS_APPENDIX.md — never the rendered block.

architext doctor/sync also runs an instruction-rule migration (crates/architext-core/src/domain/instruction_rules.rs): any Markdown bullet or numbered list item of 16+ characters in this file gets extracted into docs/architext/data/rules.json and a pointer section is appended. Tables and prose are left untouched. This guide is intentionally bullet-free so doctor leaves it alone and does not flood the curated rules.json. Keep it that way.

AGENTS.md is kept byte-identical to this file.

What Architext Is

Architext is a local, project-owned architecture / release / rules / dataflow viewer generated from strict JSON. Target projects own only JSON data (under docs/architext/data/); the viewer, schema, and tooling are owned by the globally installed architext package. The machine-readable model is the source of truth, and the rendered site is a projection for humans.

Distribution is native-only (the 1.7.0 cutover removed a previous JS CLI; there is no Node runtime and no npm channel). Architext ships as a single self-contained Rust binary with the WASM viewer embedded, delivered via install.sh, GitHub-release binaries, and architext update. See README.md for the product framing and ROADMAP.md for direction.

Read the full file on GitHub · 268 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.

2mo ago First seen · 268 lines · 3,926 tokens per session scan A cf51c661f4e1

Subscribe to this mod's changes

architext AGENTS.md is an instructions file published in the GitHub repository robot-accomplice/architext (15 stars, last pushed 2mo ago), licensed MIT. It adds 3,926 tokens to every session, about $0.0157 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.

Writing and docs

architext AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architext AGENTS.mdrobot-accomplice/architext	Instructions file	15	2mo ago	MIT	A	3,926	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

architext: Instructions file for Codex