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 shennawardana23/skillme --skill continuous-learninggit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/continuous-learning)<a href="https://agentmods.dev/skills/shennawardana23/skillme/continuous-learning"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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/shennawardana23/skillme/continuous-learning"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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 | $0.00102 | $0.01282 |
| Opus 5 | $0.00051 | $0.00641 |
| Sonnet 5 | $0.00020 | $0.00256 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
continuous-learning 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 8d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Learning (session-end extraction)
A lightweight approach to turning a Claude Code session into a reusable
skill: at the end of a session, evaluate the transcript for extractable
patterns and save the useful ones as new skill files. This is the coarse,
whole-skill version of the idea — see continuous-learning-v2 for an
atomic, confidence-scored alternative and how the two differ.
When to use this over v2
- You want something simple to reason about: one evaluation pass, one output artifact (a skill file), no confidence machinery.
- You're comfortable reviewing and approving what gets extracted rather than having it accumulate automatically.
- You don't need project-scoped vs. global separation of what's learned.
If you want atomic, per-behavior learning with confidence scores that
strengthen or decay over time, and separate handling for project-specific
vs. universal patterns, that's what continuous-learning-v2 is for —
don't try to bolt confidence scoring onto this simpler approach; use v2
directly instead.
How it works
This runs as a Stop hook — a hook that fires once, at the end of a session, rather than on every tool call:
- Session-length check — skip sessions too short to contain a real pattern (a reasonable default is 10+ substantive exchanges; a two-message session rarely has anything worth extracting).
- Pattern detection — scan the transcript for the pattern types below.
- Extraction — write useful patterns out as skill files in a
dedicated location (e.g.
~/.claude/skills/learned/), so they're available to future sessions the same way any other skill is.
Why a Stop hook specifically
- Lightweight — it runs once, not on every message, so it adds no per-turn latency.
- Complete context — by the time it fires, it has the full session transcript to reason over, rather than a partial view.
- The tradeoff (see v2's rationale) is that a Stop hook only sees sessions that end normally and only gets one shot at the whole transcript — there's no per-tool-call observation to catch behaviors mid-session.
What ships with it
1 file 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.
- 8d ago First seen · 140 lines · 102 tokens per session scan A 99799d836c9f
continuous-learning is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,282 once invoked, about $0.0005 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
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).
hello-world
A minimal test skill that greets the user and demonstrates the ASM publish workflow.