Brigade is an ecosystem for running crews of AI agents as a personal intelligence system, with local handling of credentials and support for exposing agent crews to the internet for testing. It is for people who want to organize and operate multiple AI agents using their own API keys or existing Claude, ChatGPT, Copilot, Claude Code, or Codex access. The catalogue skills provide workflows for using Brigade and its agent ecosystem.
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 spinabot/brigade --skill taskflow-inbox-triagegit clone --depth 1 https://github.com/spinabot/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/spinabot/brigade/taskflow-inbox-triage)<a href="https://agentmods.dev/skills/spinabot/brigade/taskflow-inbox-triage"><img src="https://agentmods.dev/badge/skills/spinabot/brigade/taskflow-inbox-triage.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 | $0.00049 | $0.00689 |
| Opus 5 | $0.00024 | $0.00345 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
taskflow-inbox-triage 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 8d 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.
This is a copy
92% identical to taskflow-inbox-triage — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TaskFlow inbox triage
This is a concrete example of how to think about TaskFlow without turning the core runtime into a DSL.
Goal
Triage inbox items with one owner flow:
- business → post to Slack and wait for reply
- personal → notify the owner now
- everything else → keep for end-of-day summary
Pattern
- Create one flow for the inbox batch.
- Run one detached task to classify new items.
- Persist the routing state in
stateJson. - Move to
waitingonly when an outside reply is required. - Resume the flow when classification or human input completes.
- Finish when the batch has been routed.
Suggested stateJson shape
{
"businessThreads": [],
"personalItems": [],
"eodSummary": []
}
Suggested waitJson when blocked on Slack:
{
"kind": "reply",
"channel": "slack",
"threadKey": "slack:thread-1"
}
Minimal runtime calls
const taskFlow = api.runtime.tasks.flow.fromToolContext(ctx);
const created = taskFlow.createManaged({
controllerId: "my-plugin/inbox-triage",
goal: "triage inbox",
currentStep: "classify",
stateJson: {
businessThreads: [],
personalItems: [],
eodSummary: [],
},
});
const child = taskFlow.runTask({
flowId: created.flowId,
runtime: "acp",
childSessionKey: "agent:main:subagent:classifier",
task: "Classify inbox messages",
status: "running",
startedAt: Date.now(),
lastEventAt: Date.now(),
});
if (!child.created) {
throw new Error(child.reason);
}
const waiting = taskFlow.setWaiting({
flowId: created.flowId,
expectedRevision: created.revision,
currentStep: "await_business_reply",
stateJson: {
businessThreads: ["slack:thread-1"],
personalItems: [],
eodSummary: [],
},
waitJson: {
kind: "reply",
channel: "slack",
threadKey: "slack:thread-1",
},
});
if (!waiting.applied) {
throw new Error(waiting.code);
}
const resumed = taskFlow.resume({
flowId: waiting.flow.flowId,
expectedRevision: waiting.flow.revision,
status: "running",
currentStep: "route_items",
stateJson: waiting.flow.stateJson,
});
if (!resumed.applied) {
throw new Error(resumed.code);
}
taskFlow.finish({
flowId: resumed.flow.flowId,
expectedRevision: resumed.flow.revision,
stateJson: resumed.flow.stateJson,
});
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.
- 8d ago First seen · 120 lines · 49 tokens per session scan A 88ad538c5831
taskflow-inbox-triage is a skill published in the GitHub repository spinabot/brigade (3,498 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 689 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to taskflow-inbox-triage, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
feishu-interaction
Feishu/Lark platform interaction via MCP - documents, tasks, calendar, Bitable, messaging.
operator-inbox
Maintain a provider-neutral local action queue from bounded provider observations and explicit human dispositions.
sylvia
Skill "sylvia" from markmhendrickson/ateles, covering sylvia — recurring task lifecycle daemon, identity, job, 1. neotoma task scan and 2. google calendar scan.
turdus
Skill "turdus" from markmhendrickson/ateles, covering turdus — email triage daemon, identity, job, invoice routing (immediate, not general) and aauth sub.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
钉钉企业 IM 操作
A command reference for using DingTalk, a workplace messaging and collaboration platform, through its command-line tool. It covers messages, calendars, documents, cloud files, contacts, tasks, and attendance data.