An implementation command that finds prepared tasks or saved prompts in a Clavix project and carries them out. It tracks progress and runs tests and checks after the work.

Use it to build tasks from a product-requirements workflow or execute prompts created by the improvement workflow.

It removes the need to locate the right task list or prompt manually and keeps implementation progress connected to the project plan.

implement — Command for Claude Code by that0n3guy: An implementation command that finds prepared tasks or saved…

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/that0n3guy/mealie-mcp-server-ts/implement

Clone the repo

git clone --depth 1 https://github.com/that0n3guy/mealie-mcp-server-ts

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/implement.svg)](https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/implement)

Your own site

<a href="https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/implement"><img src="https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/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 11,502 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.11502
Opus 5	$0.00000	$0.05751
Sonnet 5	$0.00000	$0.02300
Haiku 4.5	$0.00000	$0.01150

Measured 5d ago against content hash b9c0dd36a615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

implement scanned grade B 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 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

**⚠️ Never tell the user a file was saved without verifying it exists.**

.claude/commands/clavix/implement.md · 1,615 lines

How it starts

The opening of the file, as written. The whole thing — 1,615 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clavix: Implement

Time to build! This command auto-detects what to implement:

Tasks from PRD workflow - Your task list from /clavix:plan
Prompts from improve workflow - Your optimized prompts from /clavix:improve

What This Does

When you run /clavix:implement, I:

Auto-detect what to build - Check tasks.md first, then prompts/
Find your work - Load from PRD output or saved prompts
Build systematically - Tasks in order, or implement your prompt
Mark progress - Update checkboxes or prompt metadata
Verify automatically - Run tests and checks when done

You just say "implement" and I handle the rest.

Detection Priority

/clavix:implement
    │
    ├─► Check .clavix/outputs/<project>/tasks.md (all project folders)
    │       └─► If found → Task Implementation Mode
    │
    ├─► Check .clavix/outputs/summarize/tasks.md (legacy fallback)
    │       └─► If found → Task Implementation Mode (legacy)
    │
    └─► Check .clavix/outputs/prompts/*.md
            └─► If found → Prompt Execution Mode
            └─► If neither → Ask what to build

Required Confirmation Message

Before starting any implementation, you MUST output a confirmation message:

For tasks.md detection:

Found tasks.md with [N] pending tasks in [project-name]. Starting task implementation...

For prompt detection:

Found [N] saved prompt(s) in prompts/. Implementing [prompt-name]...

For legacy summarize/ fallback:

Found tasks.md with [N] pending tasks in summarize/ (legacy location). Starting task implementation...

This confirmation ensures the user knows exactly what will be implemented before any code is written.

Explicit Flags

Override auto-detection when needed:

--tasks - Force task mode (skip prompt check)
--prompt <id> - Execute specific prompt by ID
--latest - Execute most recent prompt

CLAVIX MODE: Implementation

I'm in implementation mode. Building your tasks!

Read the full file on GitHub · 1,615 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.

5d ago First seen · 1,615 lines · 0 tokens per session scan B b9c0dd36a615

Subscribe to this mod's changes

implement is a command published in the GitHub repository that0n3guy/mealie-mcp-server-ts (0 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,502 tokens. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

implement