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 matteotitta/genesys-skills --skill learngit clone --depth 1 https://github.com/matteotitta/genesys-skillsWrote 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/matteotitta/genesys-skills/learn)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/learn"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/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/matteotitta/genesys-skills/learn"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Memory Poisoning · line 64 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Excessive Agency · line 328 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00074 | $0.03845 |
| Opus 5.5 | $0.00030 | $0.01538 |
| Sonnet 5.5 | $0.00015 | $0.00769 |
| Haiku 4.5 | $0.00007 | $0.00384 |
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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn — absorb source material into the knowledge base
Process raw material into structured context. Classify it, extract what matters, file it where it belongs, and connect it to what already exists.
/steal takes from the outside. /learn absorbs from the inside.
Triggers
Invoke when user says:
/learn [file path or URL]/learn --queue(drain mode — see below)- "process this transcript"
- "add this to context"
- "learn from this [call / doc / article / page]"
- "I have a new [transcript / competitor page / doc] — file it"
Do NOT invoke when:
- User wants to extract marketing patterns from external work (use
/steal) - User wants to run a full structured research workflow (use
/company-context,/competitor-research,/icp-research) - User wants to save content they admire (use
/steal→ swipe file) - User wants to analyze a transcript for specific deliverables (use
/transcript-analysis)
--queue mode (drain the slack-capture-bot queue)
When invoked as /learn --queue with no URL/file argument:
-
Inventory the queue. Read
.claude/queue/*.md. Filter to files where frontmatter hasintent: learnANDstatus: unprocessed. If none, say "queue is empty for /learn" and exit. -
Show the user the drain plan before starting. Print a one-line summary per file:
<filename>—<source>— captured<captured_at>— reflex:<reflex>Ask: "Process all N? [y/N/select]" —selectlets the user pick a subset by number.
-
Process serially. For each approved file:
- Read the source URL/path from frontmatter
- Run the standard /learn workflow against that source (classify → extract → file)
- Use the reflex from the queue file as context for "why this was saved"
- At the standard /learn review gate (Gate 1 — quick review), gate per-file
- After completion, mark the queue file:
status: processedprocessed_at: <ISO timestamp>processed_to: <path where /learn deposited the output>
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 · 332 lines · 74 tokens per session scan A 142f90a09828
learn is a skill published in the GitHub repository matteotitta/genesys-skills (46 stars, last pushed 13d ago), licensed MIT. It adds 74 tokens to every session and 3,845 once invoked, about $0.0003 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
cargo-content
Manage the files a Cargo workspace holds — upload knowledge (PDF, CSV, text) and build native or connector-backed libraries agents retrieve from (RAG), and use files as plain storage: write and read by path, list a folder, hand out a signed or public link. Triggers: "upload this PDF", "add these docs as knowledge"…
meta-learn
Captures a completed skill session in depth: three extraction questions (what surprised you, what was wrong, what was missing) become falsifiable pattern statements, logged to /context/skill-sessions.md for meta-synthesis. Trigger on: "capture what we learned", "log this session", "save the learnings", "what did we…
meta-synthesis
Reads /context/skill-sessions.md to detect patterns that repeat across 2+ sessions, proposes new guardrails for /context/meta-patterns.md, and proposes brain updates for confirmed learnings. Run on demand or roughly weekly, not as a background job. Trigger on: "run meta-synthesis", "what patterns are emerging"…
agent-persona-builder
Design persistent AI agent personas with distinct voices, durable memory, and clear operating rules. Use when the user wants to build an internal AI agent for a portco or fund workflow, asks 'help me create an agent for X', mentions building an agent persona, wants to formalize a recurring AI workflow as a named agent…
company-moc
Build a Map of Content (MOC) for a company in an Obsidian vault — an ideas-first knowledge graph built from primary sources (decks, transcripts, standards, reports), with a hub note and linked child notes. Use when asked to "build a MOC", "map this company", "create a knowledge graph on X", or to update an existing…
category-point-of-view
Create a differentiated B2B category point of view that leads with the customer problem, defines the market shift, names the category or strategic frame, and turns it into content, distribution, and measurement guidance.