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 shimo4228/claude-harness --skill task-triagegit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/task-triage)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/task-triage"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/task-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 | $0.00234 | $0.05328 |
| Opus 5 | $0.00117 | $0.02664 |
| Sonnet 5 | $0.00047 | $0.01066 |
| Haiku 4.5 | $0.00023 | $0.00533 |
Grade A, and why
task-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 2d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Triage — judge, dispatch, verify (the human keeps the last switch)
A task ledger grows faster than it drains because filing is the cheapest action anyone can
take. This skill is one cycle of a loop that drains it — not by implementing faster, but
by putting judgment first: every open task is re-read against the code and its own start
condition, and only what survives is dispatched. resolved / rejected / withdrawn /
obsoleted count as success exactly like done.
Roles (decided 2026-08-17, ADR-0043):
| Role | Who | Does | Never does |
|---|---|---|---|
| Judge (this skill) | the triage session (Fable-tier) | premise check, worth check, better-solution check, condition check → verdict; writes kickoff packets; independently verifies build output; keeps the books | files tasks on its own initiative, confirms a drop alone, merges to main, touches rules / ADR / hooks / published artifacts unattended |
| Build | a fresh session per task (Opus-tier), in a git worktree | Phase 0 premise re-check → implement → commit on the task branch with the evidence in the commit body | changes acceptance conditions, merges, pushes, edits the ledger |
| Human | the owner | direction for tasks that need it, batch answers to the digest, the merge word | watches individual sessions (attention is the scarce resource) |
The mechanism (Workflow tool, /loop, cron, Herdr) is the substrate's; this skill covers
only what to judge and how to keep the loop from running away (loop-design-check is the
lens it was designed with).
Vocabulary — do not invent states
Ledger states are draft / accepted / in_progress / blocked and the terminals
done / resolved / rejected / withdrawn / obsoleted (ADR-0050); blocked requires 再開条件 / 照合先 / 成立時,
便乗型 rows ("次に X を触るとき") do not belong in a ledger. The definitions live in
task-stocktake — read that section before the first triage. There is no "defer".
The verdicts of a triage are the states themselves:
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.
- 2d ago Changed · +6 lines 086f70dedf64
- 7d ago First seen · 288 lines · 234 tokens per session scan A 6c32dd046f4e
task-triage is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed yesterday), licensed MIT. It adds 234 tokens to every session and 5,328 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
trailhead-view
Skill "trailhead-view" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, render the map: map [map], 🎯 destination and 🗒️ notes.
trailhead-work
Skill "trailhead-work" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, work the map: work, work one ticket whole, off the map: quick and pause, resume, split.
trailhead-chart
Skill "trailhead-chart" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, chart a new map / adopt a project: new, adopt, open a ticket on the fly: ticket and triage the inbox: inbox [issue].
trailhead
Start and drive a large project (more than one agent session can hold) as a map of decision tickets on GitHub Issues, resolving one at a time until the way to the destination is clear. Self-contained (zero external-plugin dependencies: trailhead ships its own trailhead- engine agents and needs only an authenticated gh…
trailhead-manage
Skill "trailhead-manage" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.
trailhead-capture
Skill "trailhead-capture" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.