A workflow for turning a vague AgiFlow task into a clear, testable specification. It keeps the original goal while defining the scope, success conditions, dependencies and context needed to do the work.

Use it to inspect an existing task, identify unclear requirements, propose a refined title and description, define measurable acceptance criteria and update the task after approval.

It removes guesswork before implementation begins. Clear acceptance criteria make it easier to know when the task is complete and prevent accidental expansion of the work.

refine-task — Skill for Claude Code by AgiFlow/ai-plugin

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 AgiFlow/ai-plugin --skill refine-task

Clone the repo

git clone --depth 1 https://github.com/AgiFlow/ai-plugin

Made for: Claude Code.

Or install agiflow, the plugin that ships this one along with the rest of its 10 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agiflow/ai-plugin/refine-task/github.svg)](https://agentmods.dev/skills/agiflow/ai-plugin/refine-task)

Your own site

<a href="https://agentmods.dev/skills/agiflow/ai-plugin/refine-task"><img src="https://agentmods.dev/badge/skills/agiflow/ai-plugin/refine-task/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/agiflow/ai-plugin/refine-task"><img src="https://agentmods.dev/badge/skills/agiflow/ai-plugin/refine-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 403 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00403
Opus 5.5	$0.00021	$0.00161
Sonnet 5.5	$0.00010	$0.00081
Haiku 4.5	$0.00005	$0.00040

Measured 1mo ago against content hash 5656f367407a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refine-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 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.

Origin

This is a copy

100% identical to refine-task — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/refine-task/SKILL.md · 42 lines

What it actually says

Agiflow Refine Task

Make the selected task ready for confident execution while preserving its original intent.

Workflow

Resolve the task with get_current_scope, list_projects, list_tasks, or get_task as needed.
Call get_task for full details and list_task_comments when prior decisions may affect scope.
Call list_project_statuses and list_members only when status or assignment context is relevant.
Evaluate the task for:
- Clear user or business outcome
- Concrete scope boundaries
- Objective acceptance criteria
- Known dependencies and blockers
- Appropriate priority and assignee
- Enough context to complete without guessing
Ask focused clarification questions for unresolved decisions. Do not invent requirements.
Draft the refined title, description, acceptance criteria, scope boundaries, and dependency notes.
Show the proposed changes and request approval.
After approval, call update_task with only the fields that need to change.
Call get_task again to verify the saved result.

Quality Test

Acceptance criteria must be specific, measurable, achievable within the task, relevant to its outcome, and directly verifiable. Replace phrases such as "works correctly" or "handles errors" with observable behavior.

Guardrails

Do not add new product requirements during refinement.
Do not move the task from Planning to Todo. Backlog grooming owns that transition.
Do not delete the task.
Preserve useful existing context and comments.

Response

Summarize what changed, which ambiguities were resolved, and whether the task is ready for backlog-grooming.

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.

1mo ago First seen · 42 lines · 52 tokens per session scan A 5656f367407a

Subscribe to this mod's changes

refine-task is a skill published in the GitHub repository AgiFlow/ai-plugin (4 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 403 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to refine-task, differing in 0 lines, and is treated as a copy.

Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens