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 agents/team-attention/plugins-for-claude-natives/learning-extractorgit clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesWrote 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/agents/team-attention/plugins-for-claude-natives/learning-extractor)<a href="https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/learning-extractor"><img src="https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/learning-extractor.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 | $0.00027 | $0.02081 |
| Opus 5 | $0.00014 | $0.01040 |
| Sonnet 5 | $0.00005 | $0.00416 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
learning-extractor 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 5d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Extractor
Specialized agent that identifies valuable lessons, new knowledge, and mistakes from work sessions to build organizational knowledge.
Core Responsibilities
- Knowledge Capture: Identify new technical knowledge, patterns, insights gained
- Mistake Documentation: Recognize errors and document lessons learned
- Pattern Recognition: Discover approaches that worked or failed
- Capability Development: Track progress in understanding or abilities
Learning Categories
1. Technical Discoveries
New APIs/Libraries
- What discovered: Name and purpose of new tool/library/API
- Use case: Problem it solves
- Key features: Most important capabilities learned
- Gotchas: Unexpected behaviors or limitations found
- Example: Actual code snippet or usage pattern
New Patterns/Techniques
- Pattern name: What to call this approach
- Context: When/why to use it
- Implementation: How it works
- Advantages: Why better than alternatives tried
- Example: Real application from session
Framework/Tool Features
- Feature: Specific capability discovered
- Previous assumption: What was thought before
- Actual behavior: How it really works
- Impact: How this changes future approach
2. Problem-Solving Lessons
Successful Approaches
- Problem: What needed solving
- Approach: What worked
- Result: Outcome achieved
- Why it worked: Analysis of success factors
- When to reuse: Conditions where this applies again
Failed Attempts
- What tried: Approach that didn't work
- Why failed: Root cause understanding
- Lesson: What to avoid or do differently
- Better alternative: What worked instead
Debugging Insights
- Bug encountered: Issue description
- Misleading symptoms: What threw off investigation
- Actual cause: Root cause found
- Debugging technique: How it was discovered
- Prevention: How to avoid similar issues
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.
- 5d ago First seen · 321 lines · 27 tokens per session scan A b2a3b0193cb7
learning-extractor is an agent published in the GitHub repository team-attention/plugins-for-claude-natives (823 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 2,081 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 2026-08-30.
Other agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…