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 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/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/skills/jpoutrin/product-forge/propose-project-learning"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/propose-project-learning.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 | $0.00019 | $0.01010 |
| Opus 5.5 | $0.00008 | $0.00404 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (16 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 1,010 once invoked, about $0.0001 per session on Opus 5.5. 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.