clarify-task

A task-clarification guide for turning a vague software request into clear requirements and completion criteria.

In plain words
What is it for?
Use it to inspect a task, identify ambiguity, ask focused questions, and record assumptions before planning implementation.
Why use it?
It reduces misunderstandings by exposing missing decisions and making the expected result clear to both people and coding agents.

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/patforna/auto-task/clarify-task
Any agent
npx skills add patforna/auto-task --skill clarify-task
Clone the repo
git clone --depth 1 https://github.com/patforna/auto-task

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 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 $0.00065 $0.00864
Opus 5 $0.00032 $0.00432
Sonnet 5 $0.00013 $0.00173
Haiku 4.5 $0.00006 $0.00086

Measured 2d ago against content hash b6293f488b4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarify-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 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/clarify-task/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clarify Task

Usage

/at:clarify-task <task-path> [further user instructions]

Goal

Ensure the task is clear enough so that two reasonable agents - with access to the task content and repo only - would neither complete the task in a meaningfully different way nor disagree on whether the task is done.

Context

This skill is typically run as part of a larger workflow:

create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task

As steps (e.g. clarify, plan, impl, review) typically run in new sessions, it's imperative that the task file plus repo state carry everything the next agent needs.

Task files live in the project's task store — tasks/ in the repo by default. Project config can override this and other defaults: read .claude/auto-task.config.md (project, committed) and .claude/auto-task.config.local.md (personal overrides — win on conflict) if they exist. See /at:create-task § Task Store and Project Config.

Step 1: Understand the Task

  • Read the task and explore the relevant parts of the codebase to make sure you fully understand what the task is about and ground your questions.
  • If you detect ambiguity, vagueness or implicit assumptions, do another round of deeper exploration and try to resolve.

Step 2: Identify Issues

If after completing Step 1 you conclude that two reasonable agents - with access to the task content and repo only - would either complete the task in a meaningfully different way or disagree on whether the task is done, flag it to the user.

Triggers (non-exhaustive):

  • Motivation missing - task says what but not why.
  • Incomplete content - trailing-off sentences, TODOs, TBDs, "should we...?", etc.
  • Acceptance criteria weak - vague, untestable, or missing boundary/edge cases (see /at:create-task § Acceptance criteria).
  • Unclear scope - a criterion two reasonable agents would read differently.
  • Semantic ambiguity - same term, field, column, etc. meaning different things (e.g. "days" = calendar or trading?).
  • Implicit assumptions - things the implementer must assume that aren't stated.

Read the full file on GitHub · 74 lines

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 First seen · 74 lines · 65 tokens per session scan A b6293f488b4e

Subscribe to this mod's changes

clarify-task is a skill published in the GitHub repository patforna/auto-task (3 stars, last pushed 13d ago), licensed MIT. It adds 65 tokens to every session and 864 once invoked, about $0.0003 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.