Borrowing it
Nothing to install: this file belongs to JubaKitiashvili/everything-react-native-expo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JubaKitiashvili/everything-react-native-expo/main/.claude/skills/continuous-learning-v2/SKILL.mdgit clone --depth 1 https://github.com/JubaKitiashvili/everything-react-native-expoWrote 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/jubakitiashvili/everything-react-native-expo/continuous-learning-v2)<a href="https://agentmods.dev/skills/jubakitiashvili/everything-react-native-expo/continuous-learning-v2"><img src="https://agentmods.dev/badge/skills/jubakitiashvili/everything-react-native-expo/continuous-learning-v2/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/jubakitiashvili/everything-react-native-expo/continuous-learning-v2"><img src="https://agentmods.dev/badge/skills/jubakitiashvili/everything-react-native-expo/continuous-learning-v2.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 | $0.00017 | $0.00526 |
| Opus 5 | $0.00009 | $0.00263 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00053 |
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 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.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Learning v2
This skill manages the continuous learning pipeline — observing patterns during development sessions and converting them into persistent rules and skills.
Architecture
PostToolUse hook (real-time)
→ `continuous-learning-observer.cjs` (lightweight pattern capture)
→ patterns stored in .claude/memory/observations/
/learn command (manual, comprehensive)
→ `extract-session-patterns.js` (full session analysis)
→ `analyze-patterns.js` (pattern clustering + dedup)
→ skill-generator prompt (create new content)
→ `validate-content.js` (verify new content is valid)
/retrospective command (session end)
→ `evaluate-session.js` (quality metrics + suggestions)
How It Works
Real-Time (Automatic)
The continuous-learning-observer.cjs hook runs on PostToolUse events. It:
- Captures the tool name, file paths, and outcome
- Detects repeated patterns (same fix applied > 3 times)
- Stores observations in
.claude/memory/observations/as JSON - Lightweight — adds < 50ms to each tool call
Manual Analysis (/learn)
When the user runs /learn, the pipeline:
- Reads all observations from the current session
- Clusters them by type (style fix, import pattern, architecture choice)
- Compares against existing rules and skills
- Generates candidates for new content
- Presents candidates for user approval
- Writes approved content to
.claude/rules/or.claude/skills/
Session Evaluation (/retrospective)
At session end, evaluate-session.js:
- Aggregates all metrics (files changed, tests added, build status)
- Evaluates which rules triggered and their usefulness
- Suggests rule calibration (tighten/loosen globs, adjust content)
- Generates a session quality report
Configuration
See config.json for tuning parameters:
observationThreshold: How many times a pattern must repeat before flagging (default: 3)maxObservationsPerSession: Prevent memory bloat (default: 100)autoApprove: If true, auto-approve low-risk content (default: false)contentTypes: What types to generate —["rule", "skill"]
What ships with it
8 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.
- agent-prompts/pattern-analyzer.md 1.3 KB
- agent-prompts/skill-generator.md 1.4 KB
- config.json 657 B
- hook-templates/evaluate-session.cjs.template 1.9 KB
- hook-templates/observer-hook.cjs.template 1.6 KB
- scripts/analyze-patterns.js 1.5 KB runs code
- scripts/extract-session-patterns.js 1.5 KB runs code
- scripts/validate-content.js 2.2 KB runs code
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 · 62 lines · 17 tokens per session scan A ca94498c0d1b
continuous-learning-v2 is a skill published in the GitHub repository JubaKitiashvili/everything-react-native-expo (45 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 526 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.