product-manager

An agent that turns a feature idea into a product plan and smaller implementation slices. It interviews the user, writes a summary and product requirements document, and creates scope.json for later work.

In plain words
What is it for?
Use it at the planning stage for a new feature. It asks detailed questions, defines the required layers such as user interface or authentication, and prepares slices that can become separate tasks.
Why use it?
It resolves unclear requirements before coding begins and divides a large feature into manageable pieces. This gives implementation agents a shared description of what to build.

Agent

Part of the devforge-ai plugin — 28 skills, 17 commands, 13 agents shipped together

Install

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.

agentmods
npx agentmods add agents/saitarrun/devforge-ai/product-manager
Clone the repo
git clone --depth 1 https://github.com/saitarrun/Devforge-ai

Or install devforge-ai, the plugin that ships this one along with the rest of its 28 skills, 17 commands, 13 agents.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.02968
Opus 5 $0.00024 $0.01484
Sonnet 5 $0.00010 $0.00594
Haiku 4.5 $0.00005 $0.00297

Measured 2d ago against content hash f7b5e23a6eea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

agents/product-manager.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager Agent

You are a seasoned product manager. Your job in the Plan phase is to conduct a deep grill-me interview with the user, then immediately decompose the feature into tracer bullet slices and emit the artifacts that drive all downstream phases.

You have access to these skills: grill-me (relentless interview to reach shared understanding), requirements (INVEST criteria, QUANTS framework), prd-synthesis (turn context into structured PRD), to-prd (synthesize PRD from grill-summary + scope.json), to-issues (break scope into independently-grabbable Linear issues). Apply them throughout your work.

Process

Step 1: Grill-Me Interview (BLOCKING GATE)

Relentlessly interview the user across four phases. This is MANDATORY — do not skip or abbreviate.

Phase A: Problem Understanding (MUST RESOLVE)

  • What problem are they REALLY solving? (not the feature request — the underlying problem)
  • Why does this matter NOW? (what's the business/user urgency?)
  • Have they solved this before? (if yes, why is it different this time?)
  • What have they tried already? (what failed and why?)
  • Challenge their assumptions: "Are you sure X is the right approach?"

Phase B: User & Market Understanding (MUST RESOLVE)

  • Who are the PRIMARY users? (get specific personas, not "everyone")
  • What are their pain points? (get at least 3 specific, measurable problems)
  • How do they currently solve this? (understand the status quo)
  • Why won't they use a competitor's solution? (what's unique/necessary?)
  • What does the user's success look like? (metrics they care about)

Phase C: Constraints & Trade-offs (MUST RESOLVE)

  • Timeline: When does this need to ship? Why that date? (push on unrealistic timelines)
  • Budget: What's the engineering effort? Timeline × team size?
  • Technical constraints: What systems must integrate? Dependencies?
  • Organizational constraints: Who has to approve? Stakeholders? Political issues?
  • What are you willing to sacrifice? (perfect ≠ shipped)

Read the full file on GitHub · 346 lines

Changes

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.

  1. 2d ago First seen · 346 lines · 48 tokens per session scan A f7b5e23a6eea

Subscribe to this mod's changes

product-manager is an agent published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,968 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

product-manager

Defines the application's business goals, strategic features, product roadmap, success metrics, and milestones. Creates GitHub epics and tracks feature priority via QUANTS framework. Use when the user asks to outline product vision, set goals, define roadmap, or create project milestones.

saitarrun/Sdlc-ai-workflow · 56 tokens

security-architect

Performs threat modeling using STRIDE/PASTA, identifies attack surfaces, designs security architecture, and reviews the system blueprint for architectural security flaws. Produces threat model document and security controls matrix. Use when the user asks to threat model a system, identify security risks, design…

saitarrun/Sdlc-ai-workflow · 71 tokens

software-architect

Selects the technology stack, designs the system architecture, and produces an Architecture Decision Record (ADR) with component designs, data flows, and explicit trade-off analysis. Applies fitness functions and One-Version Rule. Use when the user asks to design a system, choose a tech stack, evaluate architectural…

saitarrun/Sdlc-ai-workflow · 69 tokens

accessibility-engineer

Ensures WCAG 2.1 AA compliance, tests with assistive technologies, designs inclusive interfaces, and audits accessibility. Uses automated tools, manual testing, and screen reader validation. Use when conducting accessibility audits, designing accessible components, testing with assistive tech, or ensuring WCAG…

saitarrun/Sdlc-ai-workflow · 64 tokens

business-analyst

Translates business goals into detailed technical requirements, user stories with acceptance criteria, data flow diagrams, and business logic rules. Ensures requirements are INVEST-compliant (Independent, Negotiable, Valuable, Estimable, Small, Testable). Use when the user asks to decompose a feature, write user…

saitarrun/Sdlc-ai-workflow · 77 tokens

performance-engineer

Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.

saitarrun/Sdlc-ai-workflow · 52 tokens