define

A skill for defining a product, epic, feature, or task in a structured work-management system.

In plain words
What is it for?
It helps create product vision and requirements, epics with features, features with tasks, or individual task and bug tickets through /agn:define.
Why use it?
It turns a broad idea or request into a chosen level of work with the required planning details and, where applicable, linked child units.

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/agenturehq/agenture-loop/define
Any agent
npx skills add AgentureHQ/agenture-loop --skill define
Clone the repo
git clone --depth 1 https://github.com/AgentureHQ/agenture-loop

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,497 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 $0.00064 $0.05497
Opus 5 $0.00032 $0.02749
Sonnet 5 $0.00013 $0.01099
Haiku 4.5 $0.00006 $0.00550

Measured 2d ago against content hash 32d9d32efa40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

define 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.

plugins/agn/skills/define/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Define (/agn:define <level>)

Arguments

Position Variable Value
$0 level product, epic, feature, or task
$1+ hints Optional title or, for task, kind (task | bug)

Argument validation

If $0 is missing, stop and ask:

"What level — product, epic, feature, or task?"

If $0 is not one of product, epic, feature, task, stop and list the valid set.

Dispatch

Read $0. Run exactly one of the four workflows below.

Composition via the Planner sub-agent

For epic, feature, and task levels, composition of the unit body (and decomposition into child units, where applicable) is delegated to the Planner sub-agent (plugins/agn/agents/planner.md). This skill stays focused on user dialog, slug confirmation, and taskman.sh persistence.

The product branch does not invoke the Planner — vision/spec/requirements drafting is pre-Design and stays in the parent session. Product-level Design (architecture) lives in /agn:design product; the epic list comes from /agn:define epic calls afterward.

When a workflow below says "delegate to the Planner", invoke it via the Agent tool with subagent_type: planner and a brief containing:

  • levelepic | feature | task
  • modenew
  • title — the human-readable title
  • initial_scope — what the user said in the dialog so far (problem, objective, scope, acceptance criteria, any decomposition discussed)
  • upstream — paths to relevant docs (docs/vision.md, docs/spec.md, docs/requirements.md, docs/architecture.md; parent epic or feature file)

The Planner returns:

  • ## Body — full markdown body for the unit, matching the required sections from rules/task-composition.md.
  • ## Decomposition — ordered child list (empty for task).
  • Optional ## Questions for parent — surface to the user, gather answers, re-invoke the Planner with the updated brief.

Pipe the returned Body to ./scripts/taskman.sh new <level> --slug … --title …. For each Decomposition entry, invoke ./scripts/taskman.sh new for that child after composing its own body (which may delegate to the Planner one more level down).

Read the full file on GitHub · 498 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 · 498 lines · 64 tokens per session scan A 32d9d32efa40

Subscribe to this mod's changes

define is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 5,497 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.