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/multiplex-ai/muggle-ai-teams/learn-evalgit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/learn-eval)<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/learn-eval"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/learn-eval.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 | $0.00025 | $0.01796 |
| Opus 5 | $0.00013 | $0.00898 |
| Sonnet 5 | $0.00005 | $0.00359 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
learn-eval 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn-eval - Extract, Evaluate, then Save
Extends /learn with a quality gate, save-location decision, and knowledge-placement awareness before writing any skill file.
What to Extract
Look for TWO categories:
Category A: Technical Patterns (save as skills)
- Error Resolution Patterns — root cause + fix + reusability
- Debugging Techniques — non-obvious steps, tool combinations
- Workarounds — library quirks, API limitations, version-specific fixes
- Project-Specific Patterns — conventions, architecture decisions, integration patterns
Category B: Behavioral Rules (graduate to rules files)
- User corrections — "don't do X", "always do Y first", "stop doing Z"
- Process improvements — better ways to handle recurring situations
- Communication preferences — how the user wants information presented
- Quality standards — expectations for output quality, thoroughness, or approach
Category B items are the user's feedback about HOW you work, not WHAT you build. These are more valuable than technical patterns because they prevent the same mistakes across all future sessions.
Process
-
Review the session for extractable patterns
-
Identify the most valuable/reusable insight
-
Determine save location based on category:
Category A (Technical Patterns) → Rules or CLAUDE.md:
- Ask: "Would this pattern be useful in a different project?"
- Global (relevant rules file in
muggle-ai-teams/rules/): Generic patterns usable across 2+ projects - Project (per-repo
CLAUDE.md): Project-specific knowledge - When in doubt, choose global rules file
Category B (Behavioral Rules) → Rules files:
- Decide which rules file the learning belongs in:
Learning type Target file Why How to debug/fix bugs rules/behavior.md(Debugging section)Always-loaded behavioral rule How to process information rules/behavior.md(Processing section)Always-loaded behavioral rule Communication/output preferences rules/behavior.md(Communication section)Always-loaded behavioral rule Code quality expectations rules/core.mdAlways-loaded principle Testing/CI expectations rules/quality-gates.mdLoaded during testing Git/PR expectations rules/git.mdLoaded during git ops Agent dispatch corrections rules/agents-routing.mdAlways-loaded routing Workflow process corrections workflow/reference.mdor relevant step fileLoaded during workflow
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 · 162 lines · 25 tokens per session scan A 0cdb191e12fe
learn-eval is a command published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,796 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
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
paul:resume
Restore context from handoff and continue work.
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
dream
Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index. Use when memory files have accumulated over many sessions and need cleanup. Do NOT use for storing new decisions (use remember) or searching memory (use memory).
context-health
Dashboard de salud del contexto activo con predicción de degradación y recomendaciones de compactación. Usa cuando el usuario dice "context health", "salud del contexto", "degradation", "compactar contexto", "context overflow", "tokens", "session health", "compact", "contexto lleno". Monitorea degrdación del contexto…