implement

implement is a command for Claude Code from GRACENOBLE/fullstack-template. It costs 0 tokens per session (375 once invoked), scanned A, original, MIT.

A feature-implementation command that requires a documentation check before code is written. It asks a documentation agent to compare project docs with source code, then delegates implementation after stale or missing docs are handled.

In plain words
What is it for?
Use it to implement a feature through a documentation-first workflow, covering backend work, web work, or both.
Why use it?
It prevents coding against outdated documentation and makes documentation updates part of the implementation process. It also routes work to the appropriate backend or web agent.

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/gracenoble/fullstack-template/implement
Clone the repo
git clone --depth 1 https://github.com/GRACENOBLE/fullstack-template

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 implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/gracenoble/fullstack-template/implement.svg)](https://agentmods.dev/commands/gracenoble/fullstack-template/implement)
Your own site
<a href="https://agentmods.dev/commands/gracenoble/fullstack-template/implement"><img src="https://agentmods.dev/badge/commands/gracenoble/fullstack-template/implement.svg" alt="Measured on agentmods" height="20"></a>
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 375 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 $0.00000 $0.00375
Opus 5 $0.00000 $0.00187
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured today against content hash 45ab18d1ec6e, 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 today.

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 · 56 lines

What it actually says

Implement a feature following the Documentation-First workflow. This ensures every implementation is grounded in existing patterns and leaves the docs in a better state than it found them.

Required from user before starting

  • Feature description (what it does, which layer — backend / web / both)
  • Any constraints or decisions already made

Step 1 — Documentation check

Delegate to the docs agent:

"Check existing documentation relevant to [feature]. Read _index.md for both apps, find the relevant topic docs, compare them against their source files, and report: which docs are current, which are stale, and what's missing."

Wait for the report before proceeding.


Step 2 — Assess and decide

Based on the docs agent report:

Situation Action
Docs match code Proceed to Step 3
Docs are stale Fix the stale docs first (delegate to docs agent), then Step 3
No docs exist Note it — new docs will be created in Step 4

Do not implement against stale documentation. Update docs first.


Step 3 — Implement

Delegate to the appropriate agent (backend, web, or both).

Pass the relevant doc content as context so the agent implements to the correct patterns — not from training data.

Run /project:check at the end of this step. Do not proceed if it fails.


Step 4 — Update documentation

Delegate to the docs agent:

"Update documentation to reflect the implementation of [feature]. Files changed: [list files]. Update last_verified dates. Create new topic doc if a new topic was introduced."


Step 5 — Summary

Report:

  • What was implemented
  • Which docs were updated or created
  • Output of /project:check
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. today First seen · 56 lines · 0 tokens per session scan A 45ab18d1ec6e

Subscribe to this mod's changes

implement is a command published in the GitHub repository GRACENOBLE/fullstack-template (6 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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 2026-09-04.