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.
npx skills add richardcb/oh-my-gemini --skill implementationgit clone --depth 1 https://github.com/richardcb/oh-my-geminiWrote 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.
[](https://agentmods.dev/skills/richardcb/oh-my-gemini/implementation)<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/implementation"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/implementation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.01348 |
| Opus 5.5 | $0.00017 | $0.00539 |
| Sonnet 5.5 | $0.00009 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
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 1mo 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.
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:
AfterToolhook runs typecheck/lint after code changesphase-gatehook detects phase completionralph-retryhook 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
- Complete Phase 1 (Data Layer) before Phase 2
- Complete Phase 2 (Backend) before Phase 3
- Complete Phase 3 (Frontend) before Phase 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:
- Runs typecheck (if TypeScript)
- Runs lint (if configured)
- 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_useravailable (v0.30.0+): Instructs you to callask_userwith 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
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.
- 1mo ago First seen · 210 lines · 43 tokens per session scan A 8b2be5d08ff1
implementation is a skill published in the GitHub repository richardcb/oh-my-gemini (18 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 1,348 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
prompt-engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
meteocontrol-assistant
Specialized assistant for monitoring and analyzing solar installations via the MeteoControl VCOM API. Use it to troubleshoot production drops, triage alerts, and generate system reports.
troubleshooter
Specialized in system-wide troubleshooting using metrics and logs.
logs-expert
Expert in writing and optimizing LogsQL queries for VictoriaLogs.
metrics-expert
Expert in MetricsQL and system monitoring with VictoriaMetrics.
resume-session
Resume an interrupted Maestro session using the existing active-session file and shared phase tracking.