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 handoff-inbox-draingit 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/handoff-inbox-drain)<a href="https://agentmods.dev/skills/escoffier-labs/brigade/handoff-inbox-drain"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/handoff-inbox-drain/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/handoff-inbox-drain"><img src="https://agentmods.dev/badge/skills/escoffier-labs/brigade/handoff-inbox-drain.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 | $0.00064 | $0.00922 |
| Opus 5 | $0.00032 | $0.00461 |
| Sonnet 5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
handoff-inbox-drain 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 12d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff-inbox-drain
Drain a handoff review inbox with judgment, without owning a scheduler. Brigade stays invoke-only; this skill is the allowlist-bound agent recipe for triage.
When this applies
- A handoff draft inbox has pending or reviewed items to triage.
- An operator schedules a headless harness (
claude -p,codex exec, or equivalent) against this skill. - You are reinforcing existing memory, not inventing a parallel corpus.
Allowlist
Work only through this allowlist of Brigade surfaces and local reads:
brigade handoff listbrigade handoff show <id>brigade handoff archive <id>brigade handoff closeout(when the workspace supports it)brigade handoff lint/brigade handoff doctorfor health checks- Read/Grep of on-disk handoff files,
memory/cards/, and related indexes already present in the target
Bash is scoped to those brigade handoff … commands only. Do not expand into arbitrary filesystem writes, remote APIs, unscoped shell, or tools outside this allowlist. Stay inside the handoff inbox / memory/cards/ roots; do not follow .. or symlinks out of those trees.
Grounded-edit rules
Every edit must be grounded. You must cite existing on-disk content (handoff body, card text, or index entry) before changing anything. Prefer reinforce-in-place: edit or refresh only what you can verify against a local source of truth. Date-bumps alone are not grounded edits.
Retention (never delete)
- Never delete handoff drafts or memory cards.
- Never remove inbox items by destructive filesystem ops.
- Never prune archives, queues, or card trees.
- Archive only: uncertain or done items go through archive/closeout paths, or a needs-human file the operator already uses.
Reinforce over duplicate (#724)
brigade ingest --promote-cards reinforces an existing card on exact content fingerprint match and inboxes near-match or opposite-polarity proposals for review. When draining the inbox:
- Search existing cards and recent handoffs for the same fact or decision.
- If ingest already proposed a near-match reinforce or contradiction, honor that routing — do not create a sibling card.
- If a close match exists without an ingest proposal, reinforce that card (cite the on-disk source) instead of creating a sibling.
- If unsure, leave the draft for human review rather than splitting the corpus.
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.
- 12d ago First seen · 70 lines · 64 tokens per session scan A 2c5d04d667f3
handoff-inbox-drain is a skill published in the GitHub repository escoffier-labs/brigade (72 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 922 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…
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.
implement-task
Pick up and work on a binder Task — investigate bugs, discuss open questions, design solutions, write tests, or implement code. Use when asked to "work on", "pick up", "implement", or "fix" a task.
prd-review-framework
Use when reviewing a PRD for goal clarity, scope, assumptions, and implementation readiness.
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.