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 commands/wittyreference/twilio-claude-plugin/learngit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00034 | $0.02330 |
| Opus 5 | $0.00017 | $0.01165 |
| Sonnet 5 | $0.00007 | $0.00466 |
| Haiku 4.5 | $0.00003 | $0.00233 |
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 yesterday.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning & Knowledge System
Build and maintain deep comprehension of your project -- its architecture, decisions, gotchas, capabilities, and evolution.
Two Mindsets
Catch-up: "I've been away. What happened?" -> /learn briefing
Depth: "I need to deeply understand and articulate X." -> /learn decision, /learn gotcha
Rules
- Code exercises (no-args mode): Max 2 per session
- All other modes: No session cap -- these serve information retrieval and articulation practice
- Exercise-first, answer-second: For decision and gotcha modes -- pose the challenge BEFORE revealing the answer. This is the generation effect.
- Source-grounded feedback: Every piece of feedback cites the actual source document and path
- Decline = suppress: Only applies to code exercises, not other modes
Arguments
<user_request> $ARGUMENTS </user_request>
Mode Dispatch
Parse the first word of $ARGUMENTS:
| First word | Mode |
|---|---|
| (empty) | Code exercises (existing behavior) |
briefing or catch-up or catchup |
Briefing |
decision |
Decision deep-dive |
gotcha |
Gotcha scenario exercise |
quiz |
Rapid-fire knowledge check |
status or dashboard |
Learning coverage dashboard |
list |
List pending exercises |
skip |
Suppress code exercises |
review |
Retrieval practice |
generate |
Generate exercises |
Mode: Code Exercises (no arguments)
- Look for recent commits from autonomous work (subagents, orchestration, headless)
- Identify 2-3 interesting design decisions, patterns, or non-obvious code in the changed files
- Generate exercise questions on the spot from the most recent autonomous changes
- Present the list and ask which one to work on
- When the user picks one, present the exercise question and STOP. Wait for their response.
- After their response, provide feedback:
- Read the actual file referenced in the exercise
- Compare their prediction/understanding to what the code actually does
- If they were wrong, say so directly, explain the gap, explore why
- If they were right, confirm and optionally add deeper context
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.
- yesterday First seen · 294 lines · 34 tokens per session scan A 37d34f112f89
learn is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,330 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".