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 ultra-work-scoutgit 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/ultra-work-scout)<a href="https://agentmods.dev/skills/escoffier-labs/brigade/ultra-work-scout"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/ultra-work-scout/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/ultra-work-scout"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/ultra-work-scout.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 | $0.00051 | $0.00500 |
| Opus 5 | $0.00026 | $0.00250 |
| Sonnet 5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
ultra-work-scout 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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ultra-work-scout
Use this skill when a task is important enough to scout before changing code, especially when the user asks for "ultra work", "scout this", "use scouts", "use subagents", or "really scope this out".
Mission
Turn a large request into a small number of parallel, bounded scouting jobs, then bring the results back into one implementation path. Scouts gather context and risks; they do not replace the main agent's ownership of the final change.
Default Scout Set
Start with the smallest set that can answer independent questions:
- Surface scout: find the public commands, docs, templates, and user-facing entry points that must change.
- Install scout: trace init, upgrade, profile, and default-install paths so new users get the intended behavior.
- Verification scout: identify focused tests, full checks, and existing flaky or environment-sensitive gates.
Only add more scouts when the work naturally splits into independent repos or subsystems.
Main Agent Loop
- State the immediate local task you will keep yourself.
- Assign scouts concrete questions with disjoint read or write scopes.
- Keep moving on non-overlapping work while scouts run.
- Integrate only findings you can verify in the current tree.
- Run verification through Brigade:
brigade work verify run --target . --command "<test command>" --capture ultra-work-scout
If --capture is not available in the installed Brigade version, run:
brigade work verify run --target . --command "<test command>"
brigade outcome capture ultra-work-scout --run-id latest --kind skill
Boundaries
- Do not spawn scouts for tiny, single-file fixes.
- Do not let scouts mutate the same files unless you explicitly split ownership.
- Do not trust a scout's success claim without reading the diff or output that matters.
- Do not skip the final Brigade verify and outcome capture.
Output Contract
Finish with:
- Scout questions asked and what changed because of them.
- Files changed.
- Verification command and result.
- Any release blocker or follow-up that remains.
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.
- 11d ago First seen · 58 lines · 51 tokens per session scan A dcac8b8a6619
ultra-work-scout is a skill published in the GitHub repository escoffier-labs/brigade (72 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 500 once invoked, about $0.0003 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.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.
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…