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/raja21068/autoresearch/learngit clone --depth 1 https://github.com/raja21068/AutoResearchWrote 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/raja21068/autoresearch/learn)<a href="https://agentmods.dev/commands/raja21068/autoresearch/learn"><img src="https://agentmods.dev/badge/commands/raja21068/autoresearch/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 | $0.00008 | $0.00330 |
| Opus 5 | $0.00004 | $0.00165 |
| Sonnet 5 | $0.00002 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
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 today.
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.
This is a copy
95% identical to learn — 2 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.
What it actually says
Learn Command
Extract patterns, learnings, and reusable insights from the current session: $ARGUMENTS
Your Task
Analyze the conversation and code changes to extract:
- Patterns discovered - Recurring solutions or approaches
- Best practices applied - Techniques that worked well
- Mistakes to avoid - Issues encountered and solutions
- Reusable snippets - Code patterns worth saving
Output Format
Patterns Discovered
Pattern: [Name]
- Context: When to use this pattern
- Implementation: How to apply it
- Example: Code snippet
Best Practices Applied
- [Practice name]
- Why it works
- When to apply
Mistakes to Avoid
- [Mistake description]
- What went wrong
- How to prevent it
Suggested Skill Updates
If patterns are significant, suggest updates to:
skills/coding-standards/SKILL.mdskills/[domain]/SKILL.mdrules/[category].md
Instinct Format (for continuous-learning-v2)
{
"trigger": "[situation that triggers this learning]",
"action": "[what to do]",
"confidence": 0.7,
"source": "session-extraction",
"timestamp": "[ISO timestamp]"
}
TIP: Run /learn periodically during long sessions to capture insights before context compaction.
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.
- today First seen · 62 lines · 8 tokens per session scan A 78e4f7ab06e3
learn is a command published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 330 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to learn, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
notebook-graph
Turn a notebook knowledge base into a knowledge GRAPH — a node-link graph.json + a self-contained interactive graph.html — with NO agy calls and NO extra deps. Derives edges from entity co-occurrence within documents (works even though agy rarely emits explicit relations) plus any explicit relations. See who/what…
instinct-import
Import instincts from file or URL into project/global scope.
memory
Manage local Kodelyth Memory — recall, capture, review, and curate what your AI knows about you.
security-audit
Parallel security audit — fires security-reviewer + dependency-doctor + api-guardian simultaneously. Full threat surface in one command.
instinct-status
Show learned instincts (project + global) with confidence.
promote
Promote project-scoped instincts to global scope.