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/achitokun14/claude-universal/learngit clone --depth 1 https://github.com/Achitokun14/claude-universalWrote 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/commands/achitokun14/claude-universal/learn)<a href="https://agentmods.dev/commands/achitokun14/claude-universal/learn"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/learn.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 | $0.00026 | $0.00360 |
| Opus 5 | $0.00013 | $0.00180 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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 4d 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.
What it actually says
Capture a learning, observation, or pattern into the persistent wiki.
Steps:
- If
$ARGUMENTSis empty, ask the user: "What did you learn? (one-liner or multi-paragraph, I'll tag it)". - Determine today's date:
date +%Y-%m-%d. - Target file:
~/Desktop/ACTIVITIES/llm-wiki/$(date +%Y-%m-%d).md. - If the file does not exist, seed it from
~/Desktop/ACTIVITIES/llm-wiki/TEMPLATE.md(if that exists) or a minimal# YYYY-MM-DD\n\n. - Append an entry in this format:
## $(date +%H:%M) — <3-5 word title you generate from the insight> $ARGUMENTS **Tags:** #insight [add others: #bug #learning #pattern #gotcha #workflow as applicable] **Project:** <infer from cwd — basename of git root or cwd> - If the insight references a URL or package, also append a
- $URL — <why it matters>bullet to~/Desktop/ACTIVITIES/useful-resources.mdunder a## Manually added (YYYY-MM-DD)section. - Print a one-line confirmation:
✓ learned: <title> → llm-wiki/YYYY-MM-DD.md.
This is purely deterministic — do not invoke any LLM call, just Edit/Write.
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.
- 4d ago First seen · 28 lines · 26 tokens per session scan A a808539bb597
learn is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 360 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 2026-08-31.
Other commands, from other repositories
dev-screenshot
Use the dev screenshot script to iterate on UI changes. This builds the Go server with dev tags, starts it on an isolated port, opens the browser, and captures a screenshot for visual verification.
publish
Publish a new release of Coral to PyPI. The user provides the version number as $ARGUMENTS (e.g. "2.2.0").
crossframe-teach
Use CrossFrame Teach to explain CrossFrame concepts in plain Chinese.
bmad-correct-course
Assess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal. Use when the user says "correct course" or "propose sprint change".
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
complete
Mark active workflow session as complete, archive with lessons learned, update manifest, remove active flag.