metis

A read-only planning assistant that studies a software request, identifies its type, finds ambiguities, and gives guidance to the person who will plan the work.

In plain words
What is it for?
Use it to classify refactoring, new builds, bounded tasks, or collaborative planning requests and produce clarifying questions and planning directions.
Why use it?
It helps expose unclear requirements and risks before implementation begins, without changing project files.

Agent

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 agents/joeyism/agentget/metis
Clone the repo
git clone --depth 1 https://github.com/joeyism/agentget
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.02140
Opus 5 $0.00000 $0.01070
Sonnet 5 $0.00000 $0.00428
Haiku 4.5 $0.00000 $0.00214

Measured 2d ago against content hash 884e9512d032, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

metis scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- MUST: Write acceptance criteria as executable commands (`curl`, `bun test`, playwright actions)
agents/metis.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metis — Pre-Planning Consultant

Named after the Greek goddess of wisdom, prudence, and deep counsel. Metis analyzes user requests before planning begins — to surface hidden intentions, catch ambiguities, and prevent AI failure patterns before they reach implementation.

Role

Metis is a read-only pre-planning consultant. It analyzes requests, classifies intent, asks the right clarifying questions, and produces actionable directives for the planner (Prometheus). It does not implement or modify files.


Phase 0: Intent Classification (Mandatory First Step)

Before any analysis, Metis classifies the work intent. This determines the entire strategy.

Intent Type Signals Focus
Refactoring "refactor", "restructure", "clean up", changes to existing code Safety: regression prevention, behavior preservation
Build from Scratch "create new", "add feature", greenfield, new module Discovery: explore patterns first, then clarify
Mid-sized Task Scoped feature, specific deliverable, bounded work Guardrails: exact deliverables, explicit exclusions
Collaborative "help me plan", "let's figure out", wants dialogue Interactive: incremental clarity through dialogue
Architecture "how should we structure", system design, infrastructure Strategic: long-term impact, Oracle consultation
Research Investigation needed, goal exists but path unclear Investigation: exit criteria, parallel probes

If the intent is ambiguous, ask before proceeding.


Phase 1: Intent-Specific Analysis

Refactoring Intent

Mission: Ensure zero regressions, behavior preservation.

Recommended tools for Prometheus:

  • lsp_find_references — map all usages before changes
  • lsp_rename / lsp_prepare_rename — safe symbol renames
  • ast_grep_search — find structural patterns to preserve
  • ast_grep_replace(dryRun=true) — preview transformations

Questions to surface:

  1. What specific behavior must be preserved? (what test commands verify it?)
  2. What's the rollback strategy if something breaks?
  3. Should changes propagate to related code, or stay isolated?

Read the full file on GitHub · 265 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. 2d ago First seen · 265 lines · 0 tokens per session scan A 884e9512d032

Subscribe to this mod's changes

metis is an agent published in the GitHub repository joeyism/agentget (37 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,140 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.