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/lexfrei/ccc/learnnpx skills add lexfrei/ccc --skill learngit clone --depth 1 https://github.com/lexfrei/cccWhat 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 | $0.00014 | $0.00718 |
| Opus 5 | $0.00007 | $0.00359 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
learn 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 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.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze the current session and extract key takeaways worth preserving.
Classification
Separate findings into three categories:
Personal (~/CLAUDE.md):
- General patterns and approaches that work across projects
- Tool/language insights not specific to this codebase
- Workflow preferences discovered
- Errors caused by misunderstanding that were corrected during the session
Project (CLAUDE.md):
- Architecture decisions specific to this codebase
- Project-specific conventions and patterns
- Codebase quirks and gotchas
- Integration details with project's stack
- Errors and mistakes fixed during test implementation and runs
- Insights from code review if available
Memory (auto memory system):
- User preferences and feedback specific to this project (type: user, feedback)
- Project status, ongoing initiatives, deadlines (type: project)
- References to external systems: boards, channels, dashboards (type: reference)
- Gotchas and lessons learned that are personal experience, not codebase conventions
- Anything that is project-scoped but should NOT be committed to the repo
Fallback: no project CLAUDE.md
If the project has no CLAUDE.md (or user has no write access to repo):
- Everything from Project category goes to Memory instead
- Use memory types:
projectfor architecture/conventions,feedbackfor gotchas/corrections - Do NOT create CLAUDE.md without explicit user request
Process
- Read target files before proposing changes (~/CLAUDE.md, CLAUDE.md, MEMORY.md)
- Check MEMORY.md line count — if at or above 180 lines, propose cleanup of stale/outdated entries before adding new ones
- Check for duplicates or overlapping content across ALL targets — skip if already covered
- Skip findings if found in another file (e.g. project item already in ~/CLAUDE.md globally)
- Decide where each item fits best within existing structure (don't create new sections unless nothing fits)
- Formulate concisely, matching the style of existing content
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 · 87 lines · 14 tokens per session scan A da20d04f94b0
learn is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 14 tokens to every session and 718 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 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.