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 skills add escoffier-labs/brigade --skill brigade-workgit 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/skills/escoffier-labs/brigade/brigade-work)<a href="https://agentmods.dev/skills/escoffier-labs/brigade/brigade-work"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/brigade-work/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/skills/escoffier-labs/brigade/brigade-work"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/brigade-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01633 |
| Opus 5 | $0.00043 | $0.00816 |
| Sonnet 5 | $0.00017 | $0.00327 |
| Haiku 4.5 | $0.00009 | $0.00163 |
Grade A, and why
brigade-work 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 9d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brigade-work
Brigade only earns its keep if real work flows through it. Installed and never used, it is dead weight: the daily brief is empty, the outcome ledger never fills, and outcome rank says "ranking: none". This skill is the loop that feeds it. Check what is pending, run your verification through Brigade so it produces a signed receipt, record the outcome against the skill or card that did the work, export receipts so the next run gets an evidence brief, and hand off what you learned.
Core principle: the model never grades its own work. A real exit code captured as a Brigade verify or run receipt is the only signal that counts. Route verification through Brigade, capture the outcome, feed receipts forward via MiseLedger when installed, and the loop is honest and measured (context_eval.brief_hit_rate).
When this applies
The repo or workspace is Brigade-wired: a .brigade/ directory exists, or brigade status --target . succeeds. If neither is true, this skill does not apply (run brigade init first only if the user wants Brigade here).
The loop
1. Start: see what is pending
At the start of a work session, before deciding what to do:
brigade work brief --target . # pending work, imports, warnings, suggested next command
In a memory/operator workspace, brigade daily status --target . is the lighter equivalent. Read it first.
2. Verify THROUGH Brigade, not raw
When you would run tests or a check to confirm a change, run it through Brigade so it records the exit code:
brigade work verify run --target . --command "<your test command>" # e.g. "pytest -q", "npm test", "go test ./..."
This writes a receipt under .brigade/work/verify-runs/<run-id>/ with the real status. Running tests raw produces no signal and the ledger stays empty.
To do steps 2 and 3 in one command (so the capture is never forgotten), pass --capture:
brigade work verify run --target . --command "<test command>" --capture <id>
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 89 lines · 85 tokens per session scan A 822ce10efce8
brigade-work is a skill published in the GitHub repository escoffier-labs/brigade (72 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,633 once invoked, about $0.0004 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 skills, from other repositories
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
tree-ring-memory
Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.
ops
Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.