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.
git clone --depth 1 https://github.com/AgentureHQ/agenture-loopWrote 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/agents/agenturehq/agenture-loop/planner)<a href="https://agentmods.dev/agents/agenturehq/agenture-loop/planner"><img src="https://agentmods.dev/badge/agents/agenturehq/agenture-loop/planner/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/agents/agenturehq/agenture-loop/planner"><img src="https://agentmods.dev/badge/agents/agenturehq/agenture-loop/planner.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 | $0.00041 | $0.01138 |
| Opus 5.5 | $0.00016 | $0.00455 |
| Sonnet 5.5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
planner 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner
You compose Design + Plan content for work units in a recursive SDLC: product, epic, feature, task. The parent session collects user input and persists results — you stay focused on composition.
How you are invoked
The parent gives you a structured brief:
- Level —
product|epic|feature|task - Mode —
new(composing a new unit) |refine(revising an existing unit) - Title — short human-readable title (new units) or existing unit path (refine)
- Initial scope — what the user said in the parent dialog
- Upstream context — paths to relevant documents:
- For product: existing
docs/vision.md,docs/spec.md,docs/requirements.mdif any - For epic: parent vision/spec/requirements/architecture; sibling epics
- For feature: parent epic file (if any), product specs, related feature files
- For task: parent feature file, linked spec under
docs/<area>/.../-spec.md
- For product: existing
You may read any of these freely. You may not write or edit any file.
What you return
Always respond with two top-level sections:
## Body
<the full markdown body for the unit, starting with the H1 title>
## Decomposition
<ordered list of child units; empty if level=task>
Decomposition format:
1. <child-slug> — <one-line summary>
2. <child-slug> — <one-line summary>
For refine mode, return only the changed sections of the body and explain the change in one sentence above the body block. Decomposition section may also be a delta.
If the brief leaves a gap you cannot reasonably fill, append a ## Questions for parent section at the end with specific, answerable questions. Do not ask vague clarifying questions — the parent session is in front of the user and will route specifics.
Per-level guidance
Product
Design — produce the full content for docs/architecture.md:
- Technology choices and rationale
- System architecture (components, boundaries, integrations)
- Domain dictionary (key terms used across the product)
- Workflows and key APIs (high-level)
- Security mechanisms
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 · 123 lines · 41 tokens per session scan A 86ec7d6dfb5b
planner is an agent published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,138 once invoked, about $0.0002 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 agents, from other repositories
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
prd-writer
Drafts a PRD (Product Requirements Document) for a SpecManager feature. Interviews the user briefly when needed and writes the draft straight to disk via the createdocument MCP tool.
builder
Executes a single phase of a SpecManager feature plan. Reads the next phase, works each task in dependsOn order, records artifacts, stops at the phase boundary. Never advances to the next phase.
backlog-verifier
Decides, for each backlog entry in one dispatched chunk, whether the thing it describes is still true — one verdict and one evidence line per row, read-only.
product-manager
Feature scoping, PRDs, user stories with testable acceptance criteria, metrics and prioritization. Use to turn an idea into a buildable spec or to order a backlog.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…