Borrowing it
Nothing to install: this file belongs to escoffier-labs/brigade. 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/escoffier-labs/brigade/main/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/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/escoffier-labs/brigade/agents-md"><img src="https://agentmods.dev/badge/instructions/escoffier-labs/brigade/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 | $0.02190 | $0.02190 |
| Opus 5.5 | $0.00876 | $0.00876 |
| Sonnet 5.5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 167 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 all full
verification slots for this Git common directory are occupied. It must not be retried
with a larger timeout. Use ./scripts/verify-focused or wait for an active
Brigade receipt. Set BRIGADE_VERIFY_WAIT=<seconds> before starting a gate
to wait for a slot within a bounded deadline.
The full gate reuses CI's deterministic pytest hash shards, combines their
coverage, and enforces the 78% floor once. BRIGADE_VERIFY_SHARDS overrides
N (default: CPU count / 2, rounded down, bounded to 1 through 8).
BRIGADE_VERIFY_SLOTS overrides K (default: max(1, CPU count / N, rounded
down)). On 24 CPUs this permits three full gates with eight shards each.
Overrides must be positive integers. Coordinate overrides across linked
worktrees: each caller must use the same K to preserve the shared limit.
BRIGADE_VERIFY_LOCK_PATH names an existing slot directory or a file prefix.
The focused gate runs only named selectors, without coverage or full-gate slots.
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.
- 4d ago Changed · +15 tokens per session cf77d5ff929f
- 6d ago Changed · +1 lines · +26 tokens per session 7fe3d7ac541f
- 12d ago Changed · +11 lines · +187 tokens per session 15ab9611c75a
- 1mo 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 (81 stars, last pushed today), licensed MIT. It adds 2,190 tokens to every session, about $0.0088 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.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).