Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AgentureHQ/agenture-loopnpx agentmods add skills/agenturehq/agenture-loop/defineWrote 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.
[](https://agentmods.dev/skills/agenturehq/agenture-loop/define)<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/define"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/define/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.
<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/define"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/define.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.05497 |
| Opus 5.5 | $0.00026 | $0.02199 |
| Sonnet 5.5 | $0.00013 | $0.01099 |
| Haiku 4.5 | $0.00006 | $0.00550 |
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 2mo 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.
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:
level—epic|feature|taskmode—newtitle— the human-readable titleinitial_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 fromrules/task-composition.md.## Decomposition— ordered child list (empty fortask).- 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).
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.
- 2mo ago First seen · 498 lines · 64 tokens per session scan A 32d9d32efa40
define is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 5,497 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
youtrack
Work YouTrack as an agent: what a project configures rather than fixes, what a write changes besides the field it names, and which failures report success. Not what a work item should say.
task-creation
Write and review work items in an issue tracker: establish which reader the item is for, verify every claim it makes against the system, and give the implementer a location and acceptance criteria. Sizing and decomposition belong to tasks.
tasks
Work item decomposition — break implementation phases into sized, dependency-mapped tasks, each producing a verifiable artifact. Invoke whenever task involves the T stage of the DRAFT pipeline, decomposing phases into tasks, or creating a task breakdown.
handoff
Triage this conversation into a standalone transfer document — decisions, constraints, resource identifiers, verification state, and remaining work — for a session restart or a teammate.
backlog
Manage the project's tech debt backlog. Add, list, fix, wontfix, delete, prioritize, and suggest batch actions on tracked issues, run by the user to manage accumulated debt (skills file their findings through /.zuvo/backlog-add themselves, never through this skill). Modes: list [category], add [description], fix B- …
retro
Engineering retrospective from git metrics. Reports deployment frequency, release cycle span, churn hotspots, backlog health. Outputs narrative report with 3+ actionable items. Flags: --since, --path, explicit range argument.