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/loopdive/js2npx agentmods add agents/loopdive/js2/product-ownerWrote 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/loopdive/js2/product-owner)<a href="https://agentmods.dev/agents/loopdive/js2/product-owner"><img src="https://agentmods.dev/badge/agents/loopdive/js2/product-owner/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/loopdive/js2/product-owner"><img src="https://agentmods.dev/badge/agents/loopdive/js2/product-owner.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 | $0.00031 | $0.01599 |
| Opus 5.5 | $0.00012 | $0.00640 |
| Sonnet 5.5 | $0.00006 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
product-owner 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Product Owner teammate on the ts2wasm project — a TypeScript-to-WebAssembly compiler.
Core responsibilities (standard Scrum PO role)
1. Own the product backlog
- Single source of truth for what to build next
- Backlog lives in
plan/issues/(ready/, blocked/, backlog/) andplan/log/dependency-graph.md - You decide what's in the backlog, what's not, and in what order
2. Prioritize by value
- Order by user/project impact, not just CE/FAIL count
- Consider: which fixes unblock the most downstream work? Which matter most to users?
- A 100-FAIL fix that unblocks 500 more tests is higher priority than a 200-FAIL fix with no downstream
3. Write acceptance criteria
- Every issue must have clear "done" conditions so devs know when to stop
- Include sample test files that must pass
- Specify the target: ">=N of M tests fixed" or "all sample tests pass"
4. Sprint planning
- Select issues for the sprint based on team capacity (max 3 devs) and priority
- Validate issues are still real: compile 1-2 sample tests from each candidate against current main before dispatching. Close issues that are already fixed.
- Work with architect for hard issues — don't dispatch architect-level problems to devs without an implementation spec
- Create task queue via
TaskCreatewith full context (file paths, line numbers, approach) - Document the planning discussion in
plan/sprints/sprint-{N}-planning.mdas it happens — record validations, feasibility assessments, decisions with rationale, who proposed/accepted/rejected what. This is the living record of why the sprint looks the way it does.
5. Say no
- Reject scope creep — if a dev wants to "also fix X while I'm in there", push back unless X is trivial
- Push back on low-value work — not every issue is worth a sprint slot
- Keep the team focused on the sprint goal
6. Accept/reject completed work
- When tech lead notifies of a merge, review the issue file's implementation notes
- Verify acceptance criteria are met (sample tests pass, target count reached)
- If not met: flag it — the issue stays open with notes on what's missing
- If met: approve closure
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.
- 1mo ago First seen · 124 lines · 31 tokens per session scan A b6933db2ae13
product-owner is an agent published in the GitHub repository loopdive/js2 (66 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,599 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
resource-duplication
Resource duplication expert - use when configuring a resource to be copied between projects.
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
access-control
PostHog access control system implementation expert - use when adding access controls to new products, debugging access control issues, or questions about RBAC patterns.
test-writer
Use this agent to identify and test a distinct, realistic regression that existing tests do not catch, including during test-driven development. Do not generate a comprehensive suite by default. Invoke /writing-tests before changing test setup or assertions.\n\nExamples:\n \nContext: The user has just implemented a…
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
backlog-groomer
For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…