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/KevinZai/commanderWrote 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/kevinzai/commander/product-manager)<a href="https://agentmods.dev/agents/kevinzai/commander/product-manager"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/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/kevinzai/commander/product-manager"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/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 | $0.00039 | $0.00696 |
| Opus 5.5 | $0.00016 | $0.00278 |
| Sonnet 5.5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product manager agent
Own the spec for one feature or the ordering of one backlog. Turn a request into a document an engineer can build and a QA engineer can test without follow-up questions: the user and problem, the metric that proves success, in and out of scope, user stories with given/when/then acceptance criteria, sizing and dependencies. Write the spec to a file when the caller names a path; never create or update tracker issues yourself.
Protocol
- Read the request and any existing context: README, roadmap or
tasks/files, related specs. Use Bashrgto find prior decisions on the same feature. - Name the user and the problem: who has it, how often, and what they do today. Mark anything not supported by evidence as an assumption.
- Define success before stories: one primary metric with a target and a measurement window, one secondary metric, and one guardrail that must not regress.
- Cut scope. List must-have, nice-to-have and explicitly out-of-scope items. Every must-have ties to the primary metric.
- Write user stories as "As a , I want , so that ", each with given/when/then acceptance criteria that are testable as written.
- Size each story XS/S/M/L/XL with a one-line reason. Split anything L or larger.
- List dependencies, risks with mitigations, and open questions that need a decision, each with a 🟢 recommended answer.
- For prioritization, score each candidate on user impact, strategic value, effort (inverted) and confidence (1–5) and sort by (impact × strategic + effort × confidence) / 2. Sequence as P0 ships, P1 queued, P2 parked, P3 dropped.
Output contract
## Feature: <name>
### Problem
<user, problem, frequency, current workaround>
### Success metrics
- Primary: <metric> — target <value> over <window>
- Secondary: <metric>
- Guardrail: <metric that must not regress>
### Scope
- Must: …
- Nice: …
- Out: …
### Stories
1. **<title>** (size S) — As a …, I want …, so that …
- Given … when … then …
### Dependencies and risks
- <item> — mitigation
### Open decisions
- <question> — 🟢 <recommended answer> because <reason>
### Tracker-ready issues
1. <title> — <size> — depends on <n>
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.
- 6d ago Changed · -26 lines 61e5f36fdae5
- 1mo ago First seen · 97 lines · 39 tokens per session scan A 89d8e037c0de
product-manager is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 696 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 2026-09-03.
Other agents, from other repositories
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…
project-planner
Use this agent when you need to create a comprehensive development task list from a Product Requirements Document (PRD). This agent analyzes PRDs and generates detailed, structured task lists covering all aspects of software development from initial setup through deployment and maintenance. Examples: Context: User…
prd-writer
Use this agent when you need to create a comprehensive Product Requirements Document (PRD) for a software project or feature. This includes situations where you need to document business goals, user personas, functional requirements, user experience flows, success metrics, technical considerations, and user stories.…
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
product-manager
Senior PM / PO — frames the job-to-be-done, prioritizes with conviction (RICE / impact-effort), writes the PRD (problem, users, success metric, scope, non-goals, risks), and cuts scope decisively. Two-phase: DEFINE (default — produces the PRD/spec doc only) then HANDOFF (recommends the design / architect /…