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 automagik-dev/genie --skill learngit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/learn)<a href="https://agentmods.dev/skills/automagik-dev/genie/learn"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/learn/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/automagik-dev/genie/learn"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 56 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00023 | $0.00669 |
| Opus 5.5 | $0.00009 | $0.00268 |
| Sonnet 5.5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
learn 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 1mo 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.
/learn — Behavioral Correction
When the user corrects a mistake, diagnose which behavioral surface caused it and apply one minimal, targeted fix. Interactive — runs in the foreground with the user.
When to Use
- User corrects behavior ("no, don't do that", "you should always...") or a mistake must never recur
- A pattern of repeated errors suggests a missing rule
Flow
- Diagnose before changing anything. Read the conversation, recent changes, and relevant config to establish what went wrong and why — missing rule, stale convention, or wrong default. Name the responsible surface. If the diagnosis is ambiguous, report what you verified and ask — never guess a surface.
- Propose the minimal fix in plan mode: exactly which file changes, the content, and the rationale. One learning = one surface = one change; never batch.
- Apply after approval, then confirm what was learned.
- Persist to memory: write a feedback memory (format below) and add it to the
.claude/memory/MEMORY.mdindex so the learning survives across sessions.
Writable Surfaces
| Surface | Path | Controls |
|---|---|---|
| Project conventions | CLAUDE.md |
Commands, gotchas, coding rules |
| Agent identity | AGENTS.md |
Role, preferences, team behavior |
| Personality | SOUL.md / IDENTITY.md |
Tone, communication style |
| Global rules | ~/.claude/rules/*.md |
Cross-project behavior |
| Native memory | .claude/memory/ |
Feedback, user prefs, project context |
| Project memory | memory/ |
Project-scoped knowledge |
| Hooks | .claude/settings.json |
Event-driven automation, gates |
Never Touch
- Framework files — the installed genie plugin's
skills/andagents/ - Other projects' files — scope is the current project only
- Source code — learn changes behavior configuration, never implementation
Memory Format
.claude/memory/<name>.md:
---
name: <concise-name>
description: <one line for relevance matching>
type: feedback
---
<The rule itself>
**Why:** <the incident or reason the user gave>
**How to apply:** <when/where this guidance kicks in>
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.
- 1mo ago First seen · 62 lines · 23 tokens per session scan A 09c159e27b92
learn is a skill published in the GitHub repository automagik-dev/genie (345 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 669 once invoked, about $0.0001 per session on Opus 5.5. 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
brief
Brief the user on what they saved in a period — the thread running through it, not a list.
resurface
Pick a few old saves worth revisiting now, and say why now.
ce-compound
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.
loadout-remember
Save a durable, cross-project user preference into loadout's global fragments/profiles — or update the fragment it contradicts. Use when the user states lasting guidance that should follow them across projects and agents ("always X", "never Y", "stop doing Z"), especially when it conflicts with guidance the loadout…
agent-context
Create, validate, and maintain a structured .agent-context directory for a repository so AI agents navigate the codebase efficiently and make higher-quality decisions. Use when setting up agent context for a new repo, updating context after agent work, or catching up context after human work.
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.