implement

A workflow command for carrying out the implementation phase of a project. It finds the relevant workspace, reads the project context, and works through active tasks.

In plain words
What is it for?
Use it to select a project or task, review briefs and plans, detect changed requirements, and implement the next active todo until the listed work is complete.
Why use it?
Implementation can drift when project briefs, plans, and unfinished tasks are not checked together. This command sets the required context and identifies what should be done next.

Command for Claude Code

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/terrene-foundation/metis/implement
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,848 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 $0.00020 $0.01848
Opus 5 $0.00010 $0.00924
Sonnet 5 $0.00004 $0.00370
Haiku 4.5 $0.00002 $0.00185

Measured 2d ago against content hash d10cddbe092d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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 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.

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/implement.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 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 or todo, parse accordingly
  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>/todos/active/ to see what needs doing
  • Read files in workspaces/<project>/todos/completed/ to see what's done
  • If $ARGUMENTS specifies a specific todo, focus on that one
  • Otherwise, pick the next active todo
  • Reference plans in workspaces/<project>/02-plans/ for context
  • If any file in briefs/ was modified after specs/_index.md, STOP — briefs changed since analysis. Flag for user decision: re-run /analyze or acknowledge the brief change.

Execution Model

This phase executes under the autonomous execution model (see rules/autonomous-execution.md). Implementation is fully autonomous — agents execute in parallel, self-validate through TDD, and converge through quality gates. The human observes outcomes but does not sit in the execution loop. Pre-existing failures are fixed, not reported (zero-tolerance). Agent-to-agent delegation (reviewer, security-reviewer) is autonomous, not human-gated.

Workflow

NOTE: Run /implement repeatedly until all todos/active have been moved to todos/completed

1. Prepare todos

You MUST always use the todo-manager to create detailed todos for EVERY SINGLE TODO in todos/000-master.md.

  • Review with agents before implementation
  • Ensure that both FE and BE detailed todos exist, if applicable

2. Context anchoring (MUST run before each todo)

Before implementing ANY todo, re-read the source material that spawned it:

  1. Re-read the relevant spec files — check specs/_index.md, identify which spec files cover the domain of this todo, and read them. The spec is the authority on what to build. If the spec says create_user(name, email, password_hash), that is the signature.
  2. Re-read the plan section in 02-plans/ that this todo implements — not the whole directory, but the specific plan paragraphs. If the plan describes a DataFabric class with 3 methods, you are building that class with those 3 methods.
  3. Re-read relevant journals in workspaces/<project>/journal/ — decisions, trade-offs, and risks from analysis inform how to implement. If a journal says "chose event-driven over polling because of X," the implementation must be event-driven.
  4. Re-read the todo itself — the description, not just the title. Todos have implementation details that get ignored when agents skim titles.
  5. Read current source code before calling any existing service or function. Do not trust plans, specs, or previous todos for current method signatures — the code is the truth for what exists NOW. Specs are the truth for what SHOULD exist.

Read the full file on GitHub · 134 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 · 134 lines · 20 tokens per session scan A d10cddbe092d

Subscribe to this mod's changes

implement is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,848 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.