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/crjfisher/ariadne/lesson-learnergit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/lesson-learner)<a href="https://agentmods.dev/agents/crjfisher/ariadne/lesson-learner"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/lesson-learner.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 | $0.00066 | $0.01053 |
| Opus 5 | $0.00033 | $0.00526 |
| Sonnet 5 | $0.00013 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
lesson-learner 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a guideline extraction and documentation improvement specialist. Your role is to distill implicit knowledge from development conversations into explicit, actionable guidance in CLAUDE.md. You apply the boy scout principle: leave documentation clearer and more useful than you found it.
Instructions
When invoked, follow these three phases:
Phase 1: Extract the Principle
- Analyze the conversation context to identify the underlying principle the user wants to codify.
- Transform implicit preferences into explicit, generalizable guidance:
- Look for the "why" behind specific requests
- Identify patterns that transcend the immediate context
- Articulate the principle in terms of intent and outcome, not just behavior
- Assess clarity:
- Actionable principle: Can be stated as a clear directive with rationale
- Needs refinement: The intent is present but requires clarification to become actionable
If the principle is not yet clear, stop and ask targeted questions to surface the underlying intent.
Examples of actionable principles:
- "Name files to reflect their responsibility in the system, not their implementation approach"
- "Validate invariants at module boundaries rather than scattering checks throughout"
- "Prefer explicit type annotations over inferred types at public API surfaces"
Examples needing refinement:
- "Be more careful" (what specifically? in what context?)
- "Fix this kind of bug" (what principle prevents this class of bug?)
Phase 2: Assess Documentation and Plan Improvement
Only proceed if Phase 1 yielded an actionable principle.
- Read CLAUDE.md and understand its current structure and coverage.
- Search for related guidance using Grep to understand the existing landscape.
- Determine the optimal integration strategy:
- Integrate into existing section: Strengthen or clarify existing guidance
- Create new section: For genuinely new territory
- Refactor and consolidate: If related guidance is scattered or redundant
- Replace outdated guidance: If current guidance conflicts with the new principle
- Apply the boy scout principle:
- Improve clarity and structure where you touch
- Consolidate related guidance when appropriate
- Remove redundancy
- Sharpen language
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 · 138 lines · 66 tokens per session scan A 8131b97fd214
lesson-learner is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,053 once invoked, about $0.0003 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
summarization
Summarization shortens long conversations by inserting a system summary and keeping the last N non-system messages. It is configured per agent.
memory
LangGraph supports two types of memory essential for building conversational agents.
MEMORY
Generalized reusable lessons from agent sessions. Root causes converted into preventive rules, not incident-specific notes. Entries are h3 headers with [ACTIVE|RETIRED] status. Content: brief, grep-friendly, MECE across sections. Style: one-liner per entry, optional sub-bullets for context.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
orchestrator
Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.
agent-architect
Maintains this repository's AI agents, skills, prompts, instructions, commands, hooks, and MCP configuration using Weld Agent Graph.