brat AGENTS.md

brat AGENTS.md is an instructions file for Codex, OpenCode from neul-labs/brat. It costs 323 tokens per session, scanned A, original, MIT.

A set of instructions for brat, a tool that coordinates coding-agent work through convoys, tasks, sessions, and shared project context. It lists commands for checking status, updating work, recording comments, and saving repository knowledge.

In plain words
What is it for?
Use it when managing brat tasks or sessions, reporting progress, storing project conventions, creating memory notes, or indexing the codebase.
Why use it?
It gives agents a consistent way to find their assigned work and keep task status and project context up to date.

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/neul-labs/brat/agents-md
Clone the repo
git clone --depth 1 https://github.com/neul-labs/brat

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 brat AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neul-labs/brat/agents-md.svg)](https://agentmods.dev/instructions/neul-labs/brat/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/neul-labs/brat/agents-md"><img src="https://agentmods.dev/badge/instructions/neul-labs/brat/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 323 This file is loaded in full into every session.
When invoked 323 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 $0.00323 $0.00323
Opus 5 $0.00161 $0.00161
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00032 $0.00032

Measured 4d ago against content hash 0826497c700c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brat 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 4d 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 · 59 lines

What it actually says

Brat

This repository uses Brat for AI agent orchestration. Use brat commands for work management.

Checking Status

# Overall status (convoys, tasks, sessions)
brat status --json

# List active sessions
brat session list --json

Working on Tasks

When assigned a task, you'll have task context in .claude/current_task.md.

# Update task status as you progress
brat task update <task_id> --status running --json
brat task update <task_id> --status needs-review --json

# Add progress comments (recorded in gritee issue)
gritee issue comment <issue_id> --body "Checkpoint: implemented X, tests passing" --json

Storing Context

Store architectural observations for future agents:

# Project-level context (conventions, patterns)
gritee context set test_command "cargo test"
gritee context set build_command "cargo build"
gritee context set api_pattern "REST /api/v1/"

# Discoveries as memory issues
gritee issue create --label memory --title "[Memory] Auth flow" --body "Uses JWT..." --json

# Index codebase symbols after significant changes
gritee context index --json

Reading Context

Query existing knowledge before starting:

# Project conventions
gritee context project --json

# Previous discoveries
gritee issue list --label memory --json

# Code symbols
gritee context query <function_name> --json
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. 4d ago First seen · 59 lines · 323 tokens per session scan A 0826497c700c

Subscribe to this mod's changes

brat AGENTS.md is an instructions file published in the GitHub repository neul-labs/brat (5 stars, last pushed 2mo ago), licensed MIT. It adds 323 tokens to every session, about $0.0016 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.