continuous-learning-v2

A learning workflow that finds repeated patterns in past coding sessions and turns them into draft skills for approval. Approved drafts become reusable instructions for later work.

In plain words
What is it for?
Use it to detect repeated errors, workarounds, feedback-driven changes, debugging techniques, and project-specific practices, then review the resulting draft skills.
Why use it?
It helps capture recurring fixes, debugging methods, user preferences, and project conventions instead of rediscovering them each time.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/okminlee/everything-claude-code-ios/continuous-learning
Any agent
npx skills add OkminLee/everything-claude-code-ios --skill continuous-learning
Clone the repo
git clone --depth 1 https://github.com/OkminLee/everything-claude-code-ios

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00423
Opus 5 $0.00013 $0.00211
Sonnet 5 $0.00005 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash a77d0c937e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continuous-learning-v2 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.

skills/continuous-learning/SKILL.md · 58 lines

What it actually says

Continuous Learning v2

Automatically detect repeated patterns across sessions and promote them to learned skills.

When to Activate

  • Automatically on session end (via evaluate.js Stop hook)
  • When reviewing draft skills at session start

How It Works

Detection (evaluate.js)

At session end, the evaluate hook:

  1. Loads config.json for pattern detection settings
  2. Reads today's session file (~/.claude/sessions/)
  3. Analyzes git log and session data for patterns:
    • error_resolution — same error type fixed 3+ times
    • user_corrections — approach changed after user feedback
    • workarounds — non-standard solutions applied
    • debugging_techniques — repeated debugging patterns
    • project_specific — project-unique conventions
  4. Creates draft skills in ~/.claude/skills/learned/draft-<name>.md

Approval Flow

At next session start, session-start.js reports draft skills:

[SessionStart] 2 draft skill(s) awaiting approval
[SessionStart]   Draft: draft-error-resolution-2026-03-31.md

User decides:

  • Approve: rename to remove draft- prefix, becomes active learned skill
  • Reject: delete the draft file

Configuration (config.json)

{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "auto_approve": false,
  "patterns_to_detect": ["error_resolution", "user_corrections", ...]
}
  • extraction_threshold: low (2+), medium (3+), high (5+) occurrences
  • auto_approve: always false — human gate for quality
Files

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.

Changes

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.

  1. 2d ago First seen · 58 lines · 26 tokens per session scan A a77d0c937e9f

Subscribe to this mod's changes

continuous-learning-v2 is a skill published in the GitHub repository OkminLee/everything-claude-code-ios (58 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 423 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens