implement

A command for carrying out an existing implementation plan step by step and running its quality checks. It reads the plan and progress files before making changes.

In plain words
What is it for?
Executing plans stored under docs/thoughts, updating progress.md, loading the plan’s required skills, and running the project’s final quality gate.
Why use it?
It keeps implementation tied to the agreed plan, records completed steps, and requires problems to be fixed before the work is considered finished.

Command

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/mazumba/opencode-dockerized/implement
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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 $0.00017 $0.00561
Opus 5 $0.00009 $0.00280
Sonnet 5 $0.00003 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured yesterday against content hash f3b0a61ee499, 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 yesterday.

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.

.opencode/config/commands/implement.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute the implementation plan in docs/thoughts/$ARGUMENTS step by step and run the quality gate when done.

What to do

Read docs/thoughts/$ARGUMENTS/plan.md in full before doing anything else. If docs/thoughts/$ARGUMENTS/progress.md exists, read it too — it means a previous session started this task.

If explore is unavailable in this execution context (for example, inside a subtask agent), use direct tools (glob/grep/read) for codebase discovery and reading without asking for fallback confirmation.

Load all skills listed in the plan's "Skills to Update" section before writing any code.

Execute each step from the plan in order. For each step:

  • Announce which step you are starting.
  • Make the changes specified.
  • Run the verification command listed in the step, if any.
  • Mark the step complete in docs/thoughts/$ARGUMENTS/progress.md (see format below).
  • If verification fails, fix the issue before moving to the next step.

After all steps are complete, run the full quality gate, based on the AGENTS.md.

Fix any failures before declaring the task done.

After the quality gate passes, update any skill files listed in the plan's "Skills to Update" section to reflect the implementation changes.

Maintain docs/thoughts/$ARGUMENTS/progress.md throughout so the task can be resumed if the session is interrupted:

# Progress: <task description>

## Status
In progress / Complete

## Completed Steps
- [x] Step 1: <title>
- [x] Step 2: <title>

## Current Step
- [ ] Step 3: <title>
  <any notes on where you left off or issues encountered>

## Remaining Steps
- [ ] Step 4: <title>
- [ ] Step 5: <title>

## Issues
<any blockers or decisions made that deviate from the plan>

Update Status: Complete and remove the "Current Step" block when all steps and the quality gate pass.

Rules you must follow

  • Never create git commits.
  • Quality gate must pass before the task is declared done.
  • Update skills after implementation. Stale skills mislead future sessions.
  • Follow the plan step order. Do not skip or reorder steps without noting it in Issues.

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 17 tokens per session scan A f3b0a61ee499

Subscribe to this mod's changes

implement is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 561 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.