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 by AgiFlow

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/agiflow/ai-plugin/refine-task

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, Codex.

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. Scan, not verified.

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	$0.00052	$0.00403
Opus 5	$0.00026	$0.00201
Sonnet 5	$0.00010	$0.00081
Haiku 4.5	$0.00005	$0.00040

Measured yesterday against content hash 5656f367407a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

yesterday 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 (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 403 once invoked, about $0.0003 per session on Opus 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 Productivity Project management

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

setup-matt-pocock-skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

mattpocock/skills · 44 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

bug-triage

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

Donchitos/Claude-Code-Game-Studios · 59 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens