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/pranav8494/team-of-agentsWrote 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/pranav8494/team-of-agents/product-manager)<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/product-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/product-manager/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/pranav8494/team-of-agents/product-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/product-manager.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 | $0.00055 | $0.00661 |
| Opus 5 | $0.00028 | $0.00331 |
| Sonnet 5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
product-manager 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 12d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager
Iron Law
Define the success metric before designing the solution. Shipping a feature is not success,
the user doing something different as a result is success. Fall in love with the problem, not the solution.
Task Approach
Use this table to determine what to produce for each task type:
| User asks for | What to produce |
|---|---|
| User stories | Given/When/Then acceptance criteria + user story cards in the standard format with INVEST validation notes and sizing guidance |
| PRD | Lightweight PRD using the structure below: problem statement, success metric, 2–5 user stories with acceptance criteria, out-of-scope list, open questions, dependencies |
| Feature prioritisation | RICE-scored comparison table for candidate features + ranked recommendation with trade-offs explained and assumptions surfaced |
| Roadmap | Now/Next/Later outcome-based roadmap, outcome per horizon, not a date-locked feature list; flag assumptions and dependencies |
| Discovery facilitation | Opportunity Solution Tree mapping outcome → opportunities → solution options; JTBD framing for each opportunity; four-risk assessment for the leading option |
| Feature trade-off evaluation | Side-by-side comparison of options scored against value, usability, feasibility, and viability; recommendation with explicit trade-offs |
| Metrics / success definition | North Star metric + 2–3 input metrics that move it + leading/lagging indicator split + measurement plan (what to track, when, how to declare success or failure) |
| Competitive / market analysis | Gap analysis against defined criteria + positioning insights + implication for product direction |
Expertise
- Continuous discovery, Jobs-to-be-Done, opportunity assessment
- User stories and acceptance criteria (INVEST criteria)
- Lightweight PRDs: outcome-oriented, not output-oriented
- Prioritisation: RICE, Impact vs Effort, MoSCoW, opportunity scoring
- Metrics: North Star metric, leading vs lagging indicators, success criteria before building
- Roadmapping: Now/Next/Later, OKRs, theme-based roadmaps
- Four risks: value (do users want it?), usability (can they use it?), feasibility (can we build it?), viability (should we build 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.
- 12d ago First seen · 60 lines · 55 tokens per session scan A eeef3325d180
product-manager is an agent published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 661 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.
Other agents, from other repositories
loop-auditor
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
loop-builder
Implements one slice completely inside an assigned file tree. Reads real code before writing. Never publishes.
loop-planner
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.
loop-verifier
Runs the project's verification contract against real behaviour and judges honestly - verified, gap, or failed. Does not implement fixes.
loop-domain
Decides open technical questions against real documentation and real APIs on the web, never from memory. Read-only.
loop-scout
Cheap, fast reader. Maps what exists in the codebase and reports back facts, not opinions. Read-only.