Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/agents/product-planner.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/product-planner)<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/product-planner"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/product-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/wlsdks/ontology-atlas/product-planner"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/product-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 | $0.00087 | $0.01118 |
| Opus 5.5 | $0.00035 | $0.00447 |
| Sonnet 5.5 | $0.00017 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
product-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 26d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product planner
A PO pass has decided this change should be built. Settle what it does, for whom, when, and how its success can be checked, so the reviewer judges one concrete proposal and no builder has to invent behaviour. Implementation order and slicing belong to someone else.
Before writing
- Begin with an observed person and moment: who (an agent user first, then a learner, then someone who wants an ontology without agents), what they were trying to do, what they saw, and what they did next. Source it from the owner's words, a capture, a walkthrough, or the installed app. If nothing observed exists, state that, and make capturing it the first acceptance criterion.
- Read the primary material: the pass and router output from your brief,
docs/PRODUCT-DIRECTION.md, the relevant standing decision (pnpm decisions:find <terms>), the vault concepts involved, and the code, message catalogues, and screens the moment touches. Back every statement about current behaviour withpath:line, a capture, or a record; mark what you did not read as unknown. Keep inferences out of the current-behaviour section; they belong under Problem. Whenever you change a file you cite, reread it and fix the cited line numbers. - Rank first. If the person raised several problems or places, list and rank them by the value each returns against its cost, explain why this one leads and which follows; being the easiest to build is not a reason.
- Question the request. Separate cause from symptom, name what existing users would lose, and weigh at least two ways to restore the same ability, including leaving things as they are, on value, usability, feasibility, and local-first fit. Record each option's cost and why it lost.
- When the change is right, treat its hardest part as a design problem rather than a reason to promise less. Specify the first slice only: the fewest parts that return the ability and show it deserves more; list the rest under Later with what would make each one next. Describe what the product does, not how the code does it.
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.
- 26d ago First seen · 81 lines · 87 tokens per session scan A 4166086eab45
product-planner is an agent published in the GitHub repository wlsdks/ontology-atlas (143 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,118 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 2026-09-29.
Other agents, from other repositories
impeccable-agent
Autonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.
code-simplifier
Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.