task-triage

task-triage is a skill for Claude Code, Codex from shimo4228/claude-harness. It costs 234 tokens per session (5,328 once invoked), scanned A, original, MIT.

A task-triage workflow for reviewing every open item in a project's task ledger before sending accepted work to fresh implementation sessions.

In plain words
What is it for?
Use it to verify task premises, reject or close obsolete work, prepare implementation briefs, dispatch accepted tasks, and independently check the results.
Why use it?
It checks whether each task is still valid, worthwhile, and ready to start instead of assuming that every filed task should be built.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Use it to verify task premises, reject or close obsolete work, prepare implementation briefs, dispatch accepted tasks, and independently check the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shimo4228/claude-harness/task-triage
Install

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.

Any agent
npx skills add shimo4228/claude-harness --skill task-triage
Clone the repo
git clone --depth 1 https://github.com/shimo4228/claude-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for task-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/shimo4228/claude-harness/task-triage.svg)](https://agentmods.dev/skills/shimo4228/claude-harness/task-triage)
Your own site
<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>
Per session 234 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 086f70dedf64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

skills/task-triage/SKILL.md · 294 lines

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:

Read the full file on GitHub · 294 lines

Files

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.

Changes

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.

  1. 2d ago Changed · +6 lines 086f70dedf64
  2. 7d ago First seen · 288 lines · 234 tokens per session scan A 6c32dd046f4e

Subscribe to this mod's changes

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.