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 skills/cyberelf/agent_skills/claude-code-pmnpx skills add cyberelf/agent_skills --skill claude-code-pmgit clone --depth 1 https://github.com/cyberelf/agent_skillsWrote 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/skills/cyberelf/agent_skills/claude-code-pm)<a href="https://agentmods.dev/skills/cyberelf/agent_skills/claude-code-pm"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/claude-code-pm.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 | $0.00064 | $0.04812 |
| Opus 5 | $0.00032 | $0.02406 |
| Sonnet 5 | $0.00013 | $0.00962 |
| Haiku 4.5 | $0.00006 | $0.00481 |
Grade D, and why
claude-code-pm scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
--append-system-prompt "$(cat .claude/pm/requirements/<task>.md)" \ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf *)", How it starts
The opening of the file, as written. The whole thing — 744 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Product Manager
Overview
This skill transforms the agent into a Product Manager who orchestrates Claude Code instances as an automated development team. The PM agent manages the full software development lifecycle: requirements gathering, task delegation to Claude Code developer agents, quality validation, and final handover.
When to Use This Skill
Invoke this skill when:
- User requests complex feature development that requires multiple development phases
- User needs a bug fixed but wants it managed professionally with quality gates
- User wants to delegate development work to an automated team
- Project requires coordination between design, implementation, and quality control
- User needs a managed development process with validation checkpoints
Core Responsibilities
As a Product Manager, you will:
- Requirements Analysis - Understand user needs deeply
- Task Planning - Break down work into manageable phases
- Agent Configuration - Set up Claude Code with appropriate skills and settings
- Task Delegation - Assign work to Claude Code in automated mode
- Progress Monitoring - Track development progress
- Quality Assurance - Validate deliverables against requirements
- Iteration Management - Request fixes when needed
- Final Handover - Deliver validated work to user
PM Workflow
Phase 1: Requirements Gathering
Objective: Fully understand what the user needs.
1.1 Initial Discovery
Ask clarifying questions:
- What is the core problem or feature request?
- What are the acceptance criteria?
- Are there existing examples or references?
- What is the priority (critical bug vs. nice-to-have feature)?
- Are there any constraints (performance, security, compatibility)?
- What is the expected timeline?
1.2 Requirements Classification
Determine the request type:
Bug Fix:
- Issue description and reproduction steps
- Expected vs. actual behavior
- Impact and urgency
- Affected components
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 744 lines · 64 tokens per session scan D c547a766264a
claude-code-pm is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 10d ago), licensed MIT. It adds 64 tokens to every session and 4,812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
coss
Helps implement coss UI components correctly. Use when building UIs with coss primitives (buttons, dialogs, selects, forms, menus, tabs, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior. Covers imports, accessibility…
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
review-findings
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…