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 mhylle/claude-skills-collection --skill continuous-learninggit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/continuous-learning)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/continuous-learning"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/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/mhylle/claude-skills-collection/continuous-learning"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/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 | $0.00115 | $0.02114 |
| Opus 5 | $0.00057 | $0.01057 |
| Sonnet 5 | $0.00023 | $0.00423 |
| Haiku 4.5 | $0.00012 | $0.00211 |
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 10d 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.
**Configurable threshold** — tune via `~/.claude/config/learning.yaml`: How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Learning
Extract patterns from sessions and save them as structured skill files that future sessions can consult by trigger match. This is the layer above Claude Code's auto-memory: memory captures facts and preferences about you and your projects; continuous-learning captures reusable problem-solving patterns that need more structure than a memory entry can carry.
Scope — how this differs from auto-memory
Claude Code has a built-in memory system (~/.claude/projects/.../memory/) that captures user, feedback, project, and reference memories — short, typed entries loaded into every future conversation's context. Use that for:
- Facts about the user's role, preferences, responsibilities.
- Corrections you want applied in all future work ("don't mock the database in integration tests").
- Project-state facts like deadlines, decisions, stakeholders.
- Pointers to external systems.
This skill handles the things auto-memory doesn't:
- Triggerable patterns — full YAML files with an exact error-message trigger, root-cause analysis, and copy-pasteable fix. When that same error shows up six months later, the pattern surfaces.
- Structured templates per pattern type — not just free text. Consistent shape across error resolutions, user corrections, workarounds, debugging techniques, project-specific conventions.
- Reusable skills layer — files land in
~/.claude/skills/learned/, discoverable as portable skills across projects and machines. - Usage + confidence tracking — a pattern that's worked 5 times carries more weight than one that's worked once.
Rule of thumb: a one-line fact goes in memory. A reproducible fix-recipe or debugging playbook goes here.
When to use
Automatic triggers:
- Stop hook — runs when a Claude Code session ends. See
references/hook-setup.md. - Session timeout — same mechanism.
Manual triggers:
- After solving a particularly difficult bug.
- When the user corrects an approach (indicating a learning opportunity).
- After discovering an undocumented workaround.
- When a debugging technique proves especially effective.
- After understanding project-specific conventions.
What ships with it
5 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.
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.
- 10d ago First seen · 215 lines · 115 tokens per session scan B 164544f41723
continuous-learning is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It adds 115 tokens to every session and 2,114 once invoked, about $0.0006 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.