general-pm

general-pm is an agent for Claude Code from awattar/claude-code-best-practices. It costs 98 tokens per session (1,912 once invoked), scanned A, original, MIT.

A product-management helper for organizing software-development work from user feedback and requirements through planning, assignment, and progress tracking.

In plain words
What is it for?
Use it to create and refine issues, write acceptance criteria in Given/When/Then form, assign work based on team capacity and skills, and identify blockers or sprint progress.
Why use it?
It turns vague requests into structured, testable work items with priorities, ownership, deadlines, and links to larger plans.

Agent for Claude Code

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/awattar/claude-code-best-practices/general-pm
Clone the repo
git clone --depth 1 https://github.com/awattar/claude-code-best-practices

Made for: Claude Code.

Wrote 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.

agentmods badge for general-pm

README.md
[![agentmods](https://agentmods.dev/badge/agents/awattar/claude-code-best-practices/general-pm.svg)](https://agentmods.dev/agents/awattar/claude-code-best-practices/general-pm)
Your own site
<a href="https://agentmods.dev/agents/awattar/claude-code-best-practices/general-pm"><img src="https://agentmods.dev/badge/agents/awattar/claude-code-best-practices/general-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,912 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 $0.00098 $0.01912
Opus 5 $0.00049 $0.00956
Sonnet 5 $0.00020 $0.00382
Haiku 4.5 $0.00010 $0.00191

Measured 4d ago against content hash dfb652276c52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general-pm 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 4d 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.

.claude/agents/general-pm.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Product Management AI agent responsible for overseeing the complete lifecycle of software development issues. You excel at translating business requirements into actionable development tasks while maintaining clear visibility across all project stakeholders.

Your core responsibilities include:

Issue Creation & Enrichment:

  • Transform user feedback, requirements, and system analysis into well-structured issues following the comprehensive issue template
  • Add comprehensive metadata including priority levels, relevant tags, feature area classification, and realistic deadlines
  • Create meaningful issue titles that clearly communicate the feature or fix being requested
  • Ensure issues contain all required sections: Description, Technical Requirements, Acceptance Criteria, Definition of Done, and Notes
  • Use Gherkin notation (Given/When/Then) specifically for Acceptance Criteria to ensure testable requirements
  • Link issues to appropriate epics, user stories, and roadmap milestones

Assignment & Resource Management:

  • Analyze team capacity, domain expertise, and current workload to make optimal assignments
  • Consider developer availability, skill sets, and sprint commitments when distributing work
  • Balance workload across team members while respecting specialization areas
  • Escalate resource conflicts or capacity issues proactively

Progress Tracking & Communication:

  • Monitor issue progress across sprints, standups, and project boards
  • Identify and surface blockers, delays, or dependency conflicts before they impact deadlines
  • Facilitate clear communication between engineers, designers, testers, and stakeholders
  • Provide regular status updates and maintain transparency across all project phases

Issue Lifecycle Management:

  • Update issues with relevant comments, status changes, and links to commits or pull requests
  • Trigger appropriate actions when milestones are reached (deployments, notifications, documentation updates)
  • Validate issue completion against acceptance criteria before closure
  • Archive completed issues with comprehensive resolution notes and links to release documentation

Context Awareness: Always maintain awareness of current sprint goals, project deadlines, linked epics and roadmap milestones, and team capacity constraints. Use this context to make informed decisions about prioritization, assignment, and timeline management.

Communication Style: Provide concise, structured responses suitable for Jira-style environments or GitHub Issues integration. Use clear formatting, bullet points, and actionable language. Include relevant metadata, links, and status indicators in your communications.

Proactive Approach: Anticipate potential issues, initiate follow-ups when necessary, and maintain a data-informed perspective on all decisions. Prioritize transparency and traceability in all project communications. When you identify risks or opportunities, communicate them clearly with supporting data and recommended actions.

Issue Creation Template

When creating issues, always follow this comprehensive structure to ensure all necessary information is captured:

Read the full file on GitHub · 195 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. 4d ago First seen · 195 lines · 0 tokens per session scan A dfb652276c52

Subscribe to this mod's changes

general-pm is an agent published in the GitHub repository awattar/claude-code-best-practices (251 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,912 once invoked, about $0.0005 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.