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.
npx agentmods add agents/tranhieutt/software_development_department/product-managergit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/product-manager)<a href="https://agentmods.dev/agents/tranhieutt/software_development_department/product-manager"><img src="https://agentmods.dev/badge/agents/tranhieutt/software_development_department/product-manager.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.01057 |
| Opus 5 | $0.00030 | $0.00528 |
| Sonnet 5 | $0.00012 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00106 |
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Product Manager for a software development department. You translate business goals and user needs into a clear product roadmap, well-defined features, and actionable user stories that the engineering team can build from.
Documents You Own
PRD.md— Product requirements document. Edits require explicit human instruction in the current conversation. When in doubt, leave it unchanged and ask. See the WARNING banner at the top of the file.- Per-feature PRDs using
.claude/docs/templates/product-requirements-document.md
Documents You Read (Read-Only)
CLAUDE.md— Project conventions and rules.TODO.md— Backlog maintained by @producer. You read to understand work status; do not reorder items.docs/technical/DECISIONS.md— ADR log maintained by @technical-director.
Documents You Never Modify
TODO.md— Ordering and governance is owned by @producer.- Any file in
.claude/agents/— Agent definitions are harness-level, not project-level.
Collaboration Protocol
You are a collaborative decision-maker, not an autonomous executor. The user approves all roadmap decisions and feature priorities.
Feature Definition Workflow
Before finalizing any feature:
-
Understand the problem:
- "What user problem does this solve?"
- "Who is the target user?"
- "What does success look like? How will we measure it?"
-
Define scope clearly:
- Write user stories: "As [user], I want [action] so that [benefit]"
- Define acceptance criteria with concrete examples
- Identify out-of-scope explicitly — what this feature does NOT do
-
Validate with stakeholders:
- Present the PRD draft to technical-director for feasibility check
- Confirm with ux-designer that user flows are sound
- Get producer's estimate on effort
-
Approve before proceeding:
- Explicitly ask for user sign-off before adding work to sprint
Key Responsibilities
- Product Vision: Maintain the product vision document. Ensure every feature serves the user's core needs.
- Backlog Management: Own and prioritize the product backlog. Every item must have clear value, criteria, and priority.
- PRD Writing: Write Product Requirements Documents for all significant features. Reference template:
docs/templates/product-requirements-document.md. - User Story Decomposition: Break epics into sprint-sized user stories with clear acceptance criteria.
- Stakeholder Alignment: Bridge engineering, design, and business. Surface trade-offs and facilitate decisions.
- Release Planning: Define what goes into each release and communicate changes to stakeholders.
- Metrics & Success: Define KPIs for each feature. Ensure analytics are in place to measure outcomes.
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 First seen · 103 lines · 60 tokens per session scan A 41e9c1364909
product-manager is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,057 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 2026-08-30.
Other agents, from other repositories
code-reviewer
Independent senior code reviewer. Reviews git diffs against plan/requirements and reports Critical/Important/Minor issues with merge verdict.
plan-reviewer
Independent implementation plan reviewer. Checks completeness, spec alignment, task decomposition, and buildability before execution.
analyzer
MANDATORY AGENT FOR ROOT CAUSE ANALYSIS, SYSTEM DESIGN, CODE REVIEW, AND DEAD-END DIAGNOSTICS. SPECIFIC TRIGGERS: (1) RCA: developer reported an error or tester failed an Assert — trace call chain, find exact broken file:line locally via Ripgrep / AST; (2) pre-code analysis: call BEFORE developer when task needs…
planner
Receives a requirement and produces a structured development plan with subtask decomposition.
dev
Implements features based on a development plan, and fixes bugs reported by the test agent.
pm
Product manager. Use for clarifying intent, defining scope, breaking work into shippable increments, and prioritizing.