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.
git clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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/commands/jpoutrin/product-forge/review-skills-mapping)<a href="https://agentmods.dev/commands/jpoutrin/product-forge/review-skills-mapping"><img src="https://agentmods.dev/badge/commands/jpoutrin/product-forge/review-skills-mapping/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jpoutrin/product-forge/review-skills-mapping"><img src="https://agentmods.dev/badge/commands/jpoutrin/product-forge/review-skills-mapping.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.01963 |
| Opus 5 | $0.00005 | $0.00981 |
| Sonnet 5 | $0.00002 | $0.00393 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
review-skills-mapping 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 9d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-skills-mapping
Category: Plugin Development
Usage
/review-skills-mapping [--fix] [--verbose]
Options
| Option | Description |
|---|---|
--fix |
Auto-fix issues (add missing skills to mapping, remove invalid references) |
--verbose |
Show detailed information for each skill |
Purpose
Reviews all skills across Product Forge plugins and validates compatibility with agent-skills-mapping.yaml. Use this command to:
- Verify all skills referenced in mapping actually exist
- Find skills not included in any agent's mapping
- Detect skills with invalid structure (missing SKILL.md, bad frontmatter)
- Ensure agent-skills-mapping.yaml stays in sync with available skills
What Gets Checked
1. Skills Inventory
Scans all plugins for skills:
plugins/*/skills/*/SKILL.md
2. Mapping Validation
Cross-references agent-skills-mapping.yaml to verify:
- All referenced skills exist
- Skill names use correct format (
plugin:skill-name) - No duplicate skills in agent lists
3. Coverage Analysis
Identifies:
- Skills not mapped to any agent (orphaned)
- Agents with empty skill lists
- Skills that could be suggested for agents based on plugin affinity
Execution Instructions for Claude Code
When this command is run, Claude Code should:
1. Parse Arguments
FIX_MODE = true if --fix specified
VERBOSE = true if --verbose specified
2. Inventory All Skills
Scan for all SKILL.md files:
find plugins -path "*/skills/*/SKILL.md" -type f
For each skill, extract:
- Plugin name (from path)
- Skill name (from directory name)
- Full qualified name:
{plugin}:{skill-name} - Frontmatter fields (name, description, when)
3. Load Agent-Skills Mapping
Read the mapping file:
plugins/product-design/skills/parallel-agents/agent-skills-mapping.yaml
Parse all agents and their skill lists.
4. Cross-Reference Validation
Check 1: Referenced Skills Exist
For each skill in mapping, verify the SKILL.md exists:
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.
- 9d ago First seen · 324 lines · 11 tokens per session scan A 9676a2b2d51e
review-skills-mapping is a command published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,963 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.