scribe AGENTS.md

scribe AGENTS.md is an instructions file for Codex, OpenCode from brn-mwai/scribe. It costs 1,497 tokens per session, scanned A, original, MIT.

Repository instructions for Scribe, a system that maintains context files for AI coding agents. They describe required standards, setup steps, implementation order, testing, and which parts of AGENTS.md may be edited.

In plain words
What is it for?
Use them when working on the Scribe repository to set it up, implement its planned tasks, run checks, and preserve human-owned documentation.
Why use it?
They give an AI coding agent the project context and rules it needs before changing code, including how to verify each implementation step.

Instructions file for CodexOpenCode

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/brn-mwai/scribe/agents-md
Clone the repo
git clone --depth 1 https://github.com/brn-mwai/scribe

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.

agentmods badge for scribe AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brn-mwai/scribe/agents-md.svg)](https://agentmods.dev/instructions/brn-mwai/scribe/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/brn-mwai/scribe/agents-md"><img src="https://agentmods.dev/badge/instructions/brn-mwai/scribe/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,497 This file is loaded in full into every session.
When invoked 1,497 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 $0.01497 $0.01497
Opus 5 $0.00749 $0.00749
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00150 $0.00150

Measured 3d ago against content hash ccf003bb8167, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scribe 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 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.

AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Scribe

This file is the context layer for AI agents working on this repository. It is also a live example of what Scribe produces: the blocks between <!-- scribe:begin ... --> and <!-- scribe:end ... --> are machine-maintained; everything outside them is human-owned and never touched by Scribe.

For AI coding agents — start here

You can set up and build this project autonomously. Before writing any code, engage the coding-standards skill and apply Standards and process below.

  1. Read docs/scribe-system-design.md (the authoritative spec) and docs/IMPLEMENTATION.md (the ordered build plan).
  2. Run the Autonomous setup steps in INSTALL.md. Stop and report if any verification check fails.
  3. Implement docs/IMPLEMENTATION.md tasks in order (T0 → T10). After each task, run its acceptance check and the test suite. Do not start the next task until the current one is green.
  4. Keep the pure core (extractor, synthesizer, renderer, fingerprinter, drift gate) free of I/O so it stays unit-testable. All Orbit and GitLab access lives behind adapters.
  5. Never edit content outside Scribe markers in any AGENTS.md (including this one's human blocks). Determinism is a hard requirement: same input ⇒ byte-identical output.

Standards and process (mandatory)

Built under the team coding standards loaded in Claude Code. Apply them on every task — do not hand-roll a different process.

  • Process: follow the 7-phase coding system — reason → requirements → design → implement → test → review → deploy → monitor. The Phase 0 reasoning gate precedes any code.
  • Design framework: docs/scribe-system-design.md follows the 7-step framework (clarify → estimate → architect → detail → design → scale → verify). Scribe is a batch CLI/flow, not a high-QPS service, so estimate and scale are intentionally light — runs per repo, on a schedule, no QPS surface. Verify maps every NFR back to a design decision.
  • Quality metrics (hard gates):

Read the full file on GitHub · 126 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. 3d ago First seen · 126 lines · 1,497 tokens per session scan A ccf003bb8167

Subscribe to this mod's changes

scribe AGENTS.md is an instructions file published in the GitHub repository brn-mwai/scribe (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 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.

Related

Other instructions, from other repositories