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/sync-feedbacknpx skills add jpoutrin/product-forge --skill sync-feedbackgit 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 | $0.00011 | $0.01564 |
| Opus 5 | $0.00005 | $0.00782 |
| Sonnet 5 | $0.00002 | $0.00313 |
| Haiku 4.5 | $0.00001 | $0.00156 |
Grade B, and why
sync-feedback 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/learnings/projects -name "*.md" -path "*/feedback/*" How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Feedback
Review feedback captured from your Claude Code sessions and sync to Product Forge.
Usage
/sync-feedback # Show status (default)
/sync-feedback --process # Process captured sessions with LLM analysis
/sync-feedback --review # Review pending feedback
/sync-feedback --export # Export to GitHub issues format
Options
| Option | Description |
|---|---|
--status |
Show feedback statistics across all projects |
--process |
Process captured sessions with LLM to extract feedback |
--review |
Interactive review of pending feedback items |
--export |
Export reviewed feedback to GitHub issue format |
Feedback Location
All feedback is stored in ~/.claude/learnings/:
~/.claude/learnings/
├── projects.json # Registry of opted-in projects
├── stats.json # Global statistics
└── projects/
└── {project-slug}/
└── feedback/
├── improvement/
├── skill-idea/
├── command-idea/
├── bug-report/
└── pattern/
Workflow
1. Enable hooks → /enable-feedback-hooks
2. Work normally → Sessions captured on exit (fast, no LLM)
3. Process → /sync-feedback --process (LLM analyzes sessions)
4. Review → /sync-feedback --review
5. Submit → /sync-feedback --export → Create GitHub issue
Execution Instructions
When the user runs this command:
Process Mode (--process)
-
Run the process-sessions script:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/hooks/process-sessions.py --all -
The script will:
- Find all unprocessed sessions in
~/.claude/learnings/sessions/ - For each session, read the transcript and extract user messages
- Call
claude -pto analyze messages for feedback - Save extracted feedback items to appropriate directories
- Mark sessions as processed
- Find all unprocessed sessions in
-
Display results:
Processing sessions... [process-sessions] Processing session abc12345 for project 'product-forge' [process-sessions] Saved: improvement-add-validation.md [process-sessions] Saved: skill-idea-log-checker.md Processed 3 sessions, found 5 feedback items Run /sync-feedback --review to review extracted feedback.
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 · 241 lines · 11 tokens per session scan B f869b880ea7a
sync-feedback is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,564 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…