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 GalaxyRuler/Galactic-skills --skill meta-prompt-engineeringgit clone --depth 1 https://github.com/GalaxyRuler/Galactic-skillsWrote 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/galaxyruler/galactic-skills/meta-prompt-engineering)<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/meta-prompt-engineering"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/meta-prompt-engineering/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/galaxyruler/galactic-skills/meta-prompt-engineering"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/meta-prompt-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 3 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Memory Poisoning · line 20 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Memory Poisoning · line 76 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00223 | $0.02262 |
| Opus 5 | $0.00112 | $0.01131 |
| Sonnet 5 | $0.00045 | $0.00452 |
| Haiku 4.5 | $0.00022 | $0.00226 |
Grade A, and why
meta-prompt-engineering 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 10d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-prompt engineering
Overview
A meta-prompt is any reusable instruction layer that governs how a model interprets tasks, uses context, calls tools, delegates, verifies, recovers, and terminates. System/developer prompts, routers, tool policies, planner and verifier prompts, judge prompts, and prompt-repair prompts are all meta-prompts. A one-off user request is not.
Core principle: a meta-prompt is a small executable specification for probabilistic software, not a persona description. Write it like a versioned API contract with tests. The target is not the cleverest prompt — it is the shortest maintainable instruction contract that holds across normal, edge, adversarial, long-context, tool-error, and model-upgrade conditions.
Two modes
Same discipline, two output shapes. Pick by who loads the result.
| Single-prompt mode | Contract mode | |
|---|---|---|
| Deliverable | One copy-ready prompt | A persistent instruction layer |
| Loaded by | A human, pasting it once | A harness, every run |
| Sized by | The task | A defended token budget |
| Verified by | A pre-delivery checklist | A regression suite on held-out cases |
| Read | Single-prompt mode below + references/MODEL-ADAPTATION.md |
Everything else here |
Contract mode applies when: refactoring a system/orchestrator prompt for an unattended agent; an agent misbehaves structurally (loops, wrong or excessive tool calls, hallucinated capabilities, premature "done", leaked chatter, schema drift, injection compliance); splitting a mega-prompt into planner / executor / verifier / judge; designing delegation, handoffs, or a judge rubric; building the eval harness that decides what ships.
When a single prompt starts running unattended — scheduled, looped, or wired into an agent — it has become a contract. Switch modes rather than growing the one-shot prompt.
Keep the layers distinct — task input, context, meta-prompt, orchestration, evaluation, optimizer (references/ARCHITECTURE.md §0). The highest-leverage fix is often context architecture — which tools, memories, schemas, and subagent results land in the window — not another paragraph of prose.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 117 lines · 223 tokens per session scan A d0b8f0529552
meta-prompt-engineering is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 223 tokens to every session and 2,262 once invoked, about $0.0011 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.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…