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/jpoutrin/product-forge/copy-commandnpx skills add jpoutrin/product-forge --skill copy-commandgit clone --depth 1 https://github.com/jpoutrin/product-forgeWhat 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 | $0.00014 | $0.00971 |
| Opus 5 | $0.00007 | $0.00485 |
| Sonnet 5 | $0.00003 | $0.00194 |
| Haiku 4.5 | $0.00001 | $0.00097 |
Grade A, and why
copy-command 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Command
Copy a command from Product Forge plugins to your user-level (~/.claude/) or project-level (.claude/) directory.
Usage
# List available commands
/copy-command
# Copy to project (default)
/copy-command product-design:create-prd
# Copy to user level
/copy-command git-workflow:commit --user
# Explicit project level
/copy-command devops-data:create-rfc --project
Arguments
<plugin>:<command-name>- The command to copy inplugin:nameformat--user- Copy to~/.claude/{plugin}/commands/{name}.md--project- Copy to.claude/{plugin}/commands/{name}.md(default)
What Gets Copied
Commands are single markdown files (.md) containing:
- YAML frontmatter with description and argument hints
- Documentation and usage examples
- Execution instructions for Claude Code
Directory Structure
# Project-level (default)
.claude/
└── git-workflow/
└── commands/
└── commit.md
# User-level (--user)
~/.claude/
└── git-workflow/
└── commands/
└── commit.md
Execution Instructions
When the user runs this command:
No Arguments - List Available Commands
-
Scan Product Forge plugins cache for all available commands:
ls ~/.claude/plugins/cache/product-forge-marketplace/*/commands/*.md 2>/dev/null -
For each plugin with commands, list them with descriptions:
- Read command file frontmatter to get
description - Format as:
{plugin}:{command-name} - {description}
- Read command file frontmatter to get
-
Display formatted list:
Available commands from Product Forge: product-design: create-prd - Interactive PRD creation wizard create-qa-test - Create a new QA test procedure task-focus - Focus on a specific task with context ... git-workflow: commit - Guided git commit with atomic commit analysis rebase - Rebase local changes on remote updates code-review - Review code changes for issues ... devops-data: create-rfc - Create a new RFC technical specification create-tech-spec - Create a new Technical Specification ... Usage: /copy-command <plugin>:<command-name> [--user | --project]
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.
- 2d ago First seen · 148 lines · 14 tokens per session scan A 73d2949433e0
copy-command is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 971 once invoked, about $0.0001 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 skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…