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.
git clone --depth 1 https://github.com/CES-Ltd/LumiWrote 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/commands/ces-ltd/lumi/octo-meta-prompt)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-meta-prompt"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-meta-prompt/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/commands/ces-ltd/lumi/octo-meta-prompt"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-meta-prompt.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 | $0.00015 | $0.00237 |
| Opus 5 | $0.00008 | $0.00118 |
| Sonnet 5 | $0.00003 | $0.00047 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
octo-meta-prompt 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 13d 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.
This is a copy
81% identical to octo-meta-prompt — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/octo:meta-prompt
Your first output line MUST be: 🐙 Octopus Meta-Prompt
Generate well-structured, verifiable prompts using proven meta-prompting techniques.
Usage:
/octo:meta-prompt
/octo:meta-prompt [task description]
What it does:
- Applies Task Decomposition for complex tasks
- Uses Fresh Eyes Review (different experts for creation vs. validation)
- Builds in Iterative Verification steps
- Enforces No Guessing (explicit uncertainty disclaimers)
- Assigns Specialized Experts for subtasks
See: skill-meta-prompt for full documentation.
Generated prompt includes:
- Role definition
- Structured instructions with phases
- Expert assignments
- Verification checkpoints
- Output format specification
Example:
/octo:meta-prompt create a code review checklist
→ What is the main goal?
→ What's the expected output?
→ How important is accuracy?
→ [Generates structured prompt with techniques applied]
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.
- 13d ago First seen · 44 lines · 15 tokens per session scan A 443a39e51a9e
octo-meta-prompt is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 237 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to octo-meta-prompt, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
prompt-caching
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token cost for repeated prefixes. Triggers on prompt caching, cache breakpoint, cachecontrol, token cost, cached prefix, system prompt caching.
devkit.prompt-optimize
Provides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement. Use when you need to improve prompt quality or optimize LLM interactions.
ai
Invoke the AI/LLM Application Engineer for RAG, agents, prompt engineering, evals, tool use, and LLM guardrails.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.
golden-dataset-validation
Validation rules, schema checks, duplicate detection, and coverage analysis for golden dataset integrity. Use when validating a golden dataset, checking schema conformance, finding duplicate entries, or measuring coverage. Triggers on golden dataset validation, schema check, duplicate detection, coverage analysis…
pgvector-search
Production hybrid search with PGVector and BM25 using Reciprocal Rank Fusion, metadata filtering, and performance tuning for semantic retrieval. Use when building hybrid semantic and keyword search, tuning PGVector performance, or filtering by metadata. Triggers on pgvector, hybrid search, BM25, reciprocal rank…