metis: Command for Claude Code

.claude/commands/todos.md

todos is a command for Claude Code from terrene-foundation/metis. It costs 13 tokens per session (1,435 once invoked), scanned A, original, Apache-2.0.

A command that loads the task-list phase for the currently selected workspace.

In plain words
What is it for?
It is for preparing and storing implementation todos in the workspace’s active task directory.
Why use it?
It gathers the project brief, plans, specifications, and earlier decisions before tasks are created or resumed.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is terrene-foundation/metis's own configuration. It tells Claude Code how to work on metis itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to terrene-foundation/metis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/terrene-foundation/metis/main/.claude/commands/todos.md
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

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 todos

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/metis/todos.svg)](https://agentmods.dev/commands/terrene-foundation/metis/todos)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/metis/todos"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/todos.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00013 $0.01435
Opus 5 $0.00006 $0.00718
Sonnet 5 $0.00003 $0.00287
Haiku 4.5 $0.00001 $0.00144

Measured 7d ago against content hash df643ecbcfc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

todos 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 7d 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.

.claude/commands/todos.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Resolution

  1. If $ARGUMENTS specifies a project name, use workspaces/$ARGUMENTS/
  2. Otherwise, use the most recently modified directory under workspaces/ (excluding instructions/)
  3. If no workspace exists, ask the user to create one first
  4. Read all files in workspaces/<project>/briefs/ for user context (this is the user's input surface)

Phase Check

  • Read files in workspaces/<project>/02-plans/ for context
  • Read specs/_index.md and all relevant spec files for domain truth (MUST — see rules/specs-authority.md). If specs/_index.md does not exist, STOP — return to /analyze Step 5. Do NOT create specs during /todos.
  • Read ALL journal entries from /analyze phase — especially DECISION, TRADE-OFF, and DISCOVERY types. Journal is a read-gate, not just a write-gate.
  • Check if todos/active/ already has files (resuming)
  • All todos go into workspaces/<project>/todos/active/

Execution Model

This phase executes under the autonomous execution model (see rules/autonomous-execution.md). All effort estimates in todos MUST use autonomous execution cycles, not human-days. When referencing external plans that estimate in human-days, apply the 10x multiplier to translate. Do not phase work based on "team bandwidth" — phase based on dependency order and validation gates.

Per-session capacity budget (MUST): Each todo MUST fit within a single session's capacity — ≤500 LOC load-bearing logic, ≤5–10 simultaneous invariants, ≤3–4 call-graph hops, describable in 3 sentences. See rules/autonomous-execution.md § Per-Session Capacity Budget. Todos that exceed the budget MUST be sharded at this phase, not deferred to /implement.

The /todos approval gate is a structural gate: the human approves the plan (what and why), not the execution (how and when). Once approved, /implement executes autonomously.

Workflow

1. Review plans with specialists

Reference plans in workspaces/<project>/02-plans/ and work through every single file.

Read the full file on GitHub · 102 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. 7d ago First seen · 102 lines · 13 tokens per session scan A df643ecbcfc8

Subscribe to this mod's changes

todos is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,435 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.