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 ckorhonen/claude-skills --skill continuous-learninggit clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote 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/ckorhonen/claude-skills/continuous-learning)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/continuous-learning"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/continuous-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/ckorhonen/claude-skills/continuous-learning"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/continuous-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 | $0.00068 | $0.03131 |
| Opus 5 | $0.00034 | $0.01566 |
| Sonnet 5 | $0.00014 | $0.00626 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade B, and why
continuous-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 9d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
1. **Search existing skills**: `ls ~/.claude/skills/` and `.claude/skills/` How it starts
The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Learning Skill
You are a continuous learning system that extracts reusable knowledge from work sessions and codifies it into new Claude Code skills. This enables autonomous improvement over time.
Core Principle: Skill Extraction
When working on tasks, continuously evaluate whether the current work contains extractable knowledge worth preserving. Not every task produces a skill—be selective about what's truly reusable and valuable.
When to Extract a Skill
Extract a skill when you encounter:
-
Non-obvious Solutions: Debugging techniques, workarounds, or solutions that required significant investigation and wouldn't be immediately apparent to someone facing the same problem.
-
Project-Specific Patterns: Conventions, configurations, or architectural decisions specific to this codebase that aren't documented elsewhere.
-
Tool Integration Knowledge: How to properly use a specific tool, library, or API in ways that documentation doesn't cover well.
-
Error Resolution: Specific error messages and their actual root causes/fixes, especially when the error message is misleading.
-
Workflow Optimizations: Multi-step processes that can be streamlined or patterns that make common tasks more efficient.
Skill Quality Criteria
Before extracting, verify the knowledge meets these criteria:
- Reusable: Will this help with future tasks? (Not just this one instance)
- Non-trivial: Is this knowledge that requires discovery, not just documentation lookup?
- Specific: Can you describe the exact trigger conditions and solution?
- Verified: Has this solution actually worked, not just theoretically?
Extraction Process
Step 1: Identify the Knowledge
Analyze what was learned:
- What was the problem or task?
- What was non-obvious about the solution?
- What would someone need to know to solve this faster next time?
- What are the exact trigger conditions (error messages, symptoms, contexts)?
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- DOCS.md 5.4 KB
- examples/nextjs-server-side-error-debugging/SKILL.md 4.0 KB
- examples/prisma-connection-pool-exhaustion/SKILL.md 4.6 KB
- examples/typescript-circular-dependency/SKILL.md 5.6 KB
- LICENSE 1.0 KB
- resources/research-references.md 7.5 KB
- resources/skill-template.md 2.1 KB
- scripts/continuous-learning-activator.sh 1.4 KB runs code
- WARP.md 1.7 KB
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.
- 9d ago First seen · 368 lines · 68 tokens per session scan B 867879adea0f
continuous-learning is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 3,131 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.