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/enable-feedback-hooksnpx skills add jpoutrin/product-forge --skill enable-feedback-hooksgit 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/skills/jpoutrin/product-forge/enable-feedback-hooks)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/enable-feedback-hooks"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/enable-feedback-hooks.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 | $0.00012 | $0.00870 |
| Opus 5 | $0.00006 | $0.00435 |
| Sonnet 5 | $0.00002 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade B, and why
enable-feedback-hooks scanned grade B with 1 finding 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.
cat .claude/settings.local.json 2>/dev/null || echo '{}' How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable Feedback Hooks
Opt-in the current project to capture feedback for Product Forge improvements.
What This Does
When enabled, at the end of each Claude Code session:
- Haiku analyzes the conversation for improvement opportunities
- Feedback is saved to
~/.claude/learnings/for later review - No data leaves your machine - feedback stays local until you sync
Feedback Types Captured
- Improvements - Enhancements to existing skills, commands, or agents
- Skill ideas - New skills that could help others
- Command ideas - New commands that could be useful
- Bug reports - Issues with existing components
- Patterns - Reusable patterns from your project
Enable for Current Project
Add the Stop hook to .claude/settings.local.json:
/enable-feedback-hooks
Disable
Remove the hook from the current project:
/enable-feedback-hooks --disable
How It Works
Session ends → Haiku analyzes → Saves to ~/.claude/learnings/
↓
Use /sync-feedback to review
Privacy
- Feedback analysis happens locally via Haiku
- Feedback files stored only on your machine
- You review and choose what to submit via
/sync-feedback - Nothing is sent to Product Forge without your explicit action
Execution Instructions
When the user runs this command:
Enable Mode (default)
-
Initialize learnings directory if needed:
~/.claude/plugins/cache/product-forge-marketplace/scripts/hooks/init-learnings.sh -
Check if .claude directory exists, create if needed:
mkdir -p .claude -
Read existing settings.local.json or create empty structure:
# If exists, read it cat .claude/settings.local.json 2>/dev/null || echo '{}' -
Add the Stop hook configuration:
- Merge with existing hooks if any
- Write the following hook configuration:
{ "hooks": { "Stop": [ { "hooks": [ { "type": "prompt", "prompt": "Analyze this session for Product Forge feedback. Identify:\n1. Improvements to existing skills/commands/agents\n2. New skill/command ideas\n3. Bug reports\n4. Reusable patterns\n\nRespond JSON: {\"feedback\": [{\"type\": \"improvement|skill-idea|command-idea|bug-report|pattern\", \"title\": \"...\", \"description\": \"...\", \"target\": \"plugin/component\"}]} or {\"feedback\": []}", "timeout": 60 }, { "type": "command", "command": "python3 ~/.claude/plugins/cache/product-forge-marketplace/scripts/hooks/save-feedback.py", "timeout": 10 } ] } ] } }
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 · 138 lines · 12 tokens per session scan B c9f662142274
enable-feedback-hooks is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 870 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…