task

A routing workflow for development tasks such as features, bug fixes, refactors, integrations, and migrations. It chooses how much process the task needs based on its size and complexity.

In plain words
What is it for?
It helps classify coding requests, inspect the repository briefly, and direct the work into an appropriate task process.
Why use it?
It prevents a small change from receiving unnecessary ceremony while allowing larger work to be escalated when needed.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/progiri/craftlight/task
Any agent
npx skills add progiri/craftlight --skill task
Clone the repo
git clone --depth 1 https://github.com/progiri/craftlight

Made for: Claude Code, Codex.

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,911 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00144 $0.02911
Opus 5 $0.00072 $0.01456
Sonnet 5 $0.00029 $0.00582
Haiku 4.5 $0.00014 $0.00291

Measured yesterday against content hash ff3e8caa5701, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task 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 yesterday.

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.

plugins/craftlight/skills/task/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task — the mode router

Principle: ceremony proportional to the task. Start light by default, escalate on explicit triggers — not the other way around. The router only classifies: it asks no questions about the task's substance, writes no files, and spawns no subagents. Cheap recon is allowed — 1–2 Glob/Grep calls so the file estimate rests on the repository rather than a guess; don't read whole files and don't dig further "to be sure": underestimating is safe — escalation catches it mid-flight.

Not for this skill: a "how does this work" question, reviewing someone else's code, research — anything that doesn't change code. Realized there will be no code changes → leave the skill and answer as usual.

Step 0. Orientation and resume

There's a CRAFT.md in the root → read it first: it's the project map and the starting point after CLAUDE.md (what the project is, entry points, modules, pointers into the docs/graph/ graph). No file → don't create it at this step: bootstrapping the map happens after the gate (see "Global rule: CRAFT.md, the graph, and the glossary").

Resume interrupts classification only when there is nothing new to classify. A spec matching docs/crafts/*/SPEC.md with status in-progress and unchecked boxes:

  • The message contains a new task statement → classify the new task as usual; no blocking question — just add one FYI line to the step 3 announce: parked: "<slug>" is in-progress — say "continue the task" to get back to it.
  • A bare resume trigger ("continue the task", "where did we stop") or no task statement → show the first unchecked item and offer to continue. Agreement → open the playbook of the mode named in the spec and continue from that item. Several in-progress specs → ask which one.
  • "Not now" ≠ "abandoned": the spec stays in place; mark status abandoned only on an explicit request.
  • Deliberate gap: only M/L leave a spec, so only M/L resume — an interrupted S has no artifact to resume from.

A spec with status draft is an approval interrupted at the gate (the M/L brief was shown, the ok never arrived), not active work. A bare resume trigger → show it and ask: resume the approval or delete the draft. A new task in the message → classify the new one and fold the draft question into its gate message ("also parked: draft spec <slug> — resume its approval or delete?"). Either way: don't flip a draft to in-progress yourself (that's the confirmation gate) and don't delete it without an answer — no silent orphans.

Read the full file on GitHub · 109 lines

Files

What ships with it

9 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. yesterday First seen · 109 lines · 144 tokens per session scan A ff3e8caa5701

Subscribe to this mod's changes

task is a skill published in the GitHub repository progiri/craftlight (5 stars, last pushed 7d ago), licensed MIT. It adds 144 tokens to every session and 2,911 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens