learn-eval

learn-eval is a command for coding agents from multiplex-ai/muggle-ai-teams. It costs 25 tokens per session (1,796 once invoked), scanned A, original, MIT.

A slash command that reviews a work session for reusable technical patterns and working rules, evaluates their quality, and chooses whether to save them globally or only in the current project.

In plain words
What is it for?
Use it after a session to identify debugging techniques, workarounds, project decisions, user corrections, process improvements, communication preferences, and quality standards worth saving.
Why use it?
It helps preserve useful solutions and user preferences without saving every observation automatically. The quality check is meant to filter out weak or overly specific notes.

Command

Part of the muggle-ai-teams plugin — 28 commands, 29 agents shipped together

Install

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.

agentmods
npx agentmods add commands/multiplex-ai/muggle-ai-teams/learn-eval
Clone the repo
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teams

Or install muggle-ai-teams, the plugin that ships this one along with the rest of its 28 commands, 29 agents.

Wrote 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.

agentmods badge for learn-eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/learn-eval.svg)](https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/learn-eval)
Your own site
<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>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 0cdb191e12fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/learn-eval.md · 162 lines

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)

  1. Error Resolution Patterns — root cause + fix + reusability
  2. Debugging Techniques — non-obvious steps, tool combinations
  3. Workarounds — library quirks, API limitations, version-specific fixes
  4. Project-Specific Patterns — conventions, architecture decisions, integration patterns

Category B: Behavioral Rules (graduate to rules files)

  1. User corrections — "don't do X", "always do Y first", "stop doing Z"
  2. Process improvements — better ways to handle recurring situations
  3. Communication preferences — how the user wants information presented
  4. 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

  1. Review the session for extractable patterns

  2. Identify the most valuable/reusable insight

  3. 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.md Always-loaded principle
    Testing/CI expectations rules/quality-gates.md Loaded during testing
    Git/PR expectations rules/git.md Loaded during git ops
    Agent dispatch corrections rules/agents-routing.md Always-loaded routing
    Workflow process corrections workflow/reference.md or relevant step file Loaded during workflow

Read the full file on GitHub · 162 lines

Changes

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.

  1. 5d ago First seen · 162 lines · 25 tokens per session scan A 0cdb191e12fe

Subscribe to this mod's changes

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.

Related

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…

yonatangross/orchestkit · 62 tokens

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…

yonatangross/orchestkit · 64 tokens

paul:resume

Restore context from handoff and continue work.

ChristopherKahler/paul · 13 tokens

retex

Retex - Capture lesson learned dans memory après fix, rollback, erreur.

FlorianBruniaux/claude-code-ultimate-guide · 14 tokens

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).

yonatangross/orchestkit · 55 tokens

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…

doncheli/don-cheli-sdd · 77 tokens