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/propose-project-learningnpx skills add jpoutrin/product-forge --skill propose-project-learninggit 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/propose-project-learning)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/propose-project-learning"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/propose-project-learning.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 | $0.00019 | $0.01010 |
| Opus 5 | $0.00010 | $0.00505 |
| Sonnet 5 | $0.00004 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade B, and why
propose-project-learning 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 4d 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.
Review later with: cat ~/.claude/learnings/projects/{project-slug}/proposals/ How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Propose Project Learning
Retrospect on the current session and propose learnings for the project's CLAUDE.md.
Purpose
After working on a project, identify patterns, conventions, preferences, and rules that should be documented in the project's CLAUDE.md to improve future sessions.
Usage
/propose-project-learning # Analyze and propose learnings
/propose-project-learning --save # Save proposal to ~/.claude/learnings/
What This Captures
| Category | Examples |
|---|---|
| Code conventions | Naming patterns, file organization, import ordering |
| Architecture decisions | Preferred patterns, avoided anti-patterns |
| Tool preferences | Test frameworks, linters, formatters |
| Project-specific rules | Business logic constraints, domain terminology |
| Workflow preferences | Commit style, PR conventions, review process |
Execution Instructions
When the user runs this command:
1. Analyze Current Session
Review the conversation history for:
- Corrections made - When the user corrected Claude's approach
- Explicit preferences - "Always use X", "Never do Y", "Prefer Z"
- Repeated patterns - Consistent choices across multiple files
- Project conventions - Naming, structure, organization patterns
- Tool/framework specifics - Project-specific configurations or usage
2. Check Existing CLAUDE.md
Read the project's CLAUDE.md (if exists) to avoid duplicates:
cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found"
Also check for CLAUDE.local.md:
cat CLAUDE.local.md 2>/dev/null
3. Generate Proposal
Format the proposal as:
# Proposed Learnings for CLAUDE.md
Based on this session, consider adding these to your project's CLAUDE.md:
## Code Conventions
- Use `snake_case` for all Python function names
- Prefer dataclasses over plain dicts for structured data
## Architecture
- All API endpoints go through the service layer, never direct DB access
- Use repository pattern for database operations
## Testing
- Use pytest fixtures, not setUp/tearDown methods
- Mock external services at the client level, not individual methods
## Project-Specific
- The `core` module should have no dependencies on other app modules
- All dates are stored as UTC, converted to local time only in templates
---
To add these to your CLAUDE.md:
1. Review each suggestion
2. Copy relevant items to CLAUDE.md
3. Adjust wording to match your style
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.
- 4d ago First seen · 164 lines · 19 tokens per session scan B 80247b6d016d
propose-project-learning is a skill published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,010 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…