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 agentmods add skills/fmarzochi/egc/continuous-learning-v2npx skills add Fmarzochi/EGC --skill continuous-learning-v2git clone --depth 1 https://github.com/Fmarzochi/EGCWrote 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/fmarzochi/egc/continuous-learning-v2)<a href="https://agentmods.dev/skills/fmarzochi/egc/continuous-learning-v2"><img src="https://agentmods.dev/badge/skills/fmarzochi/egc/continuous-learning-v2.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.02939 |
| Opus 5 | $0.00024 | $0.01470 |
| Sonnet 5 | $0.00010 | $0.00588 |
| Haiku 4.5 | $0.00005 | $0.00294 |
Grade B, and why
continuous-learning-v2 scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If you previously copied `observe.sh` into `~/.gemini/settings.json`, remove that duplicate `PreToolUse` / `PostToolUse` block. Duplicating the plugin hook causes double execution and `${GEMINI_PLUGIN_ROOT}` resolution e This is a copy
91% identical to continuous-learning-v2 — 83 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Learning v2.1 - Instinct
-Based Architecture
An advanced learning system that turns your Gemini Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.
v2.1 adds project-scoped instincts: React patterns stay in your React project, Python conventions stay in your Python project, and universal patterns (like "always validate input") are shared globally.
When to Activate
- Setting up automatic learning from Gemini Code sessions
- Configuring instinct-based behavior extraction via hooks
- Tuning confidence thresholds for learned behaviors
- Reviewing, exporting, or importing instinct libraries
- Evolving instincts into full skills, commands, or agents
- Managing project-scoped vs global instincts
- Promoting instincts from project to global scope
What's New in v2.1
| Feature | v2.0 | v2.1 |
|---|---|---|
| Storage | Global (~/.gemini/homunculus/) | Project-scoped (projects//) |
| Scope | All instincts apply everywhere | Project-scoped + global |
| Detection | None | git remote URL / repo path |
| Promotion | N/A | Project → global when seen in 2+ projects |
| Commands | 4 (status/evolve/export/import) | 6 (+promote/projects) |
| Cross-project | Contamination risk | Isolated by default |
What's New in v2 (vs v1)
| Feature | v1 | v2 |
|---|---|---|
| Observation | Stop hook (session end) | PreToolUse/PostToolUse (100% reliable) |
| Analysis | Main context | Background agent (Haiku) |
| Granularity | Full skills | Atomic "instincts" |
| Confidence | None | 0.3-0.9 weighted |
| Evolution | Direct to skill | Instincts -> cluster -> skill/command/agent |
| Sharing | None | Export/import instincts |
The Instinct Model
An instinct is a small learned behavior:
---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
scope: project
project_id: "a1b2c3d4e5f6"
project_name: "my-react-app"
---
# Prefer Functional Style
## Action
Use functional patterns over classes when appropriate.
## Evidence
- Observed 5 instances of functional pattern preference
- User corrected class-based approach to functional on 2025-01-15
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.
- agents/observer-loop.sh 11 KB runs code
- agents/observer.md 7.2 KB
- agents/session-guardian.sh 6.2 KB runs code
- agents/start-observer.sh 7.2 KB runs code
- config.json 135 B
- hooks/observe.sh 17 KB runs code
- scripts/detect-project.sh 7.9 KB runs code
- scripts/instinct-cli.py 55 KB runs code
- scripts/test_parse_instinct.py 32 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.
- 2d ago First seen · 346 lines · 48 tokens per session scan B d5ee472258a0
continuous-learning-v2 is a skill published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 2,939 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 91% identical to continuous-learning-v2, differing in 83 lines, and is treated as a copy.
Other skills, from other repositories
mem9
Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
lov-search-chat
从本机 Ataru 记忆索引里召回过去的 AI 会话上下文，返回可定位的命中与原文片段。 Use when asked what was discussed, decided, or fixed in an earlier session.
learn-this
Teach the user a topic and persist what they learn as queryable vault memory, grounded in NotebookLM. Vault-native companion to /teach.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.