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 bendrucker/claude --skill triagegit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/triage)<a href="https://agentmods.dev/skills/bendrucker/claude/triage"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/triage/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/bendrucker/claude/triage"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/triage.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 | $0.00030 | $0.00796 |
| Opus 5.5 | $0.00012 | $0.00318 |
| Sonnet 5.5 | $0.00006 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
things: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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Today List Triage
Group, prioritize, defer, and reorder the Things Today list.
Every step runs through the things MCP server's tools. When those tools are absent, tailgate is unreachable and there is nothing to triage against. Say so rather than falling back to the CLI scripts, which reach Things only from the machine running it.
Query
list_todos with list: "today". Filter to open items.
Each todo carries id, name, creationDate, dueDate, activationDate, and a notes preview. get_todo serves one todo's full notes when a decision needs them.
Repeating Task Detection
Apply the midnight heuristic: a task is a repeating instance when creationDate ends with T00:00:00, midnight local time in ISO. Manually created tasks carry non-zero hours, minutes, or seconds.
Things refuses to reschedule a repeating todo. A when update is a no-op on one: the write reports success and the todo stays where it was. That covers Defer, Drop, and the reschedule reorder_todos runs on. Keep every repeating instance out of all three, whether or not it is overdue.
Completion is the only disposal Things accepts on one. Report the overdue repeating instances as a group and offer that, and leave the rest scheduled where they are.
Grouping
Group the remaining items by area first and tag second, for batch triage.
Triage Questions
Per group, use AskUserQuestion:
- Keep: stays on Today for prioritization
- Defer: to tomorrow, next week, someday, or a specific date
- Complete: mark done
- Drop: move to Someday
Offer a repeating instance Keep and Complete only. Defer and Drop both write when, which it rejects.
Batch Operations
One update_todos call per decision group, passing every id in that group:
- Defer:
whenastomorrow,someday,yyyy-mm-dd, or natural language likenext week - Complete:
completed: true - Drop:
when: "someday"
Batches rate-limit to 250 operations per 10 seconds, so group by target rather than calling per todo.
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.
- 1mo ago Changed · +5 lines 1deac46f03eb
- 1mo ago First seen · 72 lines · 30 tokens per session scan A 8774b5af58ac
things:triage is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 796 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
recipe-plan
Create work plan from design document and obtain plan approval.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
recruit-init
Uma habilidade que prepara um espaço de trabalho para recrutamento, com pastas, documentos de referência, registros e instruções para agentes de programação. Ela verifica dependências como Node.js, ferramentas de vagas e, opcionalmente, o Feishu.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
scout-briefing
Launch a Scout morning briefing session as a background process. Auto-detects mode (morning briefing, consolidation, or weekend briefing) from the current time and day.
scout-dream
Launch a Scout dreaming session as a background process. Processes feedback, does KB deep work, and works on wishlist items.