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.
npx agentmods add instructions/escoffier-labs/brigade/agents-mdgit clone --depth 1 https://github.com/escoffier-labs/brigadeWrote 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/escoffier-labs/brigade/agents-md)<a href="https://agentmods.dev/instructions/escoffier-labs/brigade/agents-md"><img src="https://agentmods.dev/badge/instructions/escoffier-labs/brigade/agents-md.svg" alt="Measured on agentmods" 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 | $0.01962 | $0.01962 |
| Opus 5 | $0.00981 | $0.00981 |
| Sonnet 5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
brigade 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Brigade is a zero-runtime-dependency Python CLI for agent memory, handoffs, and
local guardrails, published to PyPI as brigade-cli. Source lives in
src/brigade/, tests in tests/, harness/depth/include manifests in
src/brigade/templates/.
Installing, evaluating, or adapting Brigade for a user's workspace? Follow
docs/agents-guide.md instead. This file is for
developing Brigade itself; the contributor policy lives in CONTRIBUTING.md.
Definition of Done
Development slices use the focused gate through Brigade:
brigade work verify run --target . --argv-json '["./scripts/verify-focused","<pytest-selector>"]' --capture brigade-work
./scripts/verify-focused runs ruff lint, ruff format check, the version-sync
check, managed snapshot, template-profile snapshot, mypy, and only the named
pytest selectors. Report the actual result, paste any failure verbatim, and
never claim success you did not observe.
Reserve the full coverage gate for pull requests, merges, releases, and verification-infrastructure changes. Run it once through Brigade:
brigade work verify run --target . --argv-json '["./scripts/verify"]' --timeout 3600 --capture brigade-work
--timeout 3600 bounds the known-long integration gate and is not permission
to retry status 75.
Do not pass --no-reuse for a full gate. Status 75 means another full
verification is already running for this checkout. It must not be retried
with a larger timeout. Use ./scripts/verify-focused or wait for the active
Brigade receipt.
CI-only jobs still cover work that is slower, platform-oriented, or depends on
extra checkout/install context: content-guard, repo-metadata,
install-from-source, quickstart-smoke, and windows-native-acceptance.
The local ./scripts/verify gate is the full coverage gate. Do not treat it
as a replacement for those CI-only release and public-repo checks.
Setup, if .venv/ is missing:
python -m venv .venv && source .venv/bin/activate && pip install -e ".[dev]"
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.
- 5d ago First seen · 155 lines · 1,962 tokens per session scan A 7ae72b50118c
brigade AGENTS.md is an instructions file published in the GitHub repository escoffier-labs/brigade (72 stars, last pushed today), licensed MIT. It adds 1,962 tokens to every session, about $0.0098 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.
Other instructions, from other repositories
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
kb AGENTS.md
AGENTS.md instructions for hraness/kb, a project described as: A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.
superlocalmemory copilot-instructions.md
Copilot instructions for qualixar/superlocalmemory, covering superlocalmemory (slm) — agent rules, session start, remember, recall and optimize (fail-open).