implementation

implementation is a skill for Claude Code, Codex from richardcb/oh-my-gemini. It costs 43 tokens per session (1,348 once invoked), scanned A, original, MIT.

A skill for carrying out an existing technical plan in ordered phases. It reads the plan and project context, tracks completed tasks, and implements the next tasks in sequence.

In plain words
What is it for?
Use it when a project has a plan and you need to build the planned data, backend, frontend, or other phases task by task.
Why use it?
It prevents planned work from being done out of order and uses hooks for checks such as type checking and linting after code changes.

Skill for Claude CodeCodex

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 skills/richardcb/oh-my-gemini/implementation
Any agent
npx skills add richardcb/oh-my-gemini --skill implementation
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Claude Code, Codex.

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 implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/implementation.svg)](https://agentmods.dev/skills/richardcb/oh-my-gemini/implementation)
Your own site
<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/implementation"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,348 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 $0.00043 $0.01348
Opus 5 $0.00022 $0.00674
Sonnet 5 $0.00009 $0.00270
Haiku 4.5 $0.00004 $0.00135

Measured 4d ago against content hash 8b2be5d08ff1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation 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 4d 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.

skills/implementation/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Skill

Goal

Execute a technical plan systematically, following established phases, completing tasks in order.

Activation Triggers

  • User says "implement", "build", "execute the plan", or "start coding"
  • A technical plan exists and it is time to write code
  • User runs /omg:implement

Hook Integration

Hooks handle verification automatically:

  • AfterTool hook runs typecheck/lint after code changes
  • phase-gate hook detects phase completion
  • ralph-retry hook handles persistence mode

You no longer need to manually remember verification steps.

Process

1. Load Plan & Context

# Find the plan file
find . -name "tasks_*.md" -o -name "plan.md" 2>/dev/null | head -5

# Load project context
cat GEMINI.md 2>/dev/null | head -50
cat conductor/tech-stack.md 2>/dev/null | head -30

2. Identify Current State

Parse the plan to find:

  • Which tasks are already complete [x]
  • Which task is next [ ]
  • Which phase we're in

3. Execute Sequentially

Work through tasks in order within each phase.

Execution Rules

Phase Order is Mandatory

  1. Complete Phase 1 (Data Layer) before Phase 2
  2. Complete Phase 2 (Backend) before Phase 3
  3. Complete Phase 3 (Frontend) before Phase 4
  4. Never skip ahead

Task Order Within Phases

  • Execute tasks in numerical order (1.0, 1.1, 1.2...)
  • Complete all sub-tasks before marking parent complete
  • Don't start new parent task until previous is done

Automatic Verification (via Hooks)

After you modify code files, the AfterTool hook automatically:

  1. Runs typecheck (if TypeScript)
  2. Runs lint (if configured)
  3. Injects any errors into context

If errors appear, fix them before proceeding to the next task.

Phase Gates (via Hooks)

When you complete a phase, the phase-gate hook:

  • ask_user available (v0.30.0+): Instructs you to call ask_user with a yes/no verification question. Use this to confirm with the developer before proceeding to the next phase.
  • Advisory mode (default): Shows a message suggesting verification
  • Strict mode: Requires explicit user confirmation

Read the full file on GitHub · 210 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. 4d ago First seen · 210 lines · 43 tokens per session scan A 8b2be5d08ff1

Subscribe to this mod's changes

implementation is a skill published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,348 once invoked, about $0.0002 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 2026-08-30.