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 xcrft/mastermind --skill mastermind-prompt-refinergit clone --depth 1 https://github.com/xcrft/mastermindWrote 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/xcrft/mastermind/mastermind-prompt-refiner)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-prompt-refiner"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-prompt-refiner/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/xcrft/mastermind/mastermind-prompt-refiner"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-prompt-refiner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 85 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 98 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 118 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00073 | $0.00986 |
| Opus 5.5 | $0.00029 | $0.00394 |
| Sonnet 5.5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
mastermind-prompt-refiner 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt refiner
Produce a bounded handoff without silently replacing the user's source request. The next consumer receives both the original text and a normalized brief, so constraints lost in rewriting remain recoverable.
When to use
- The user explicitly asks to improve, rewrite, or package a prompt.
- A cold agent will receive no conversation history and the raw request is genuinely ambiguous, contradictory, or bundles separate deliverables.
- A reusable prompt needs placeholders and a stable output contract.
Do not activate just because the user writes informally. If the current agent can answer or implement the request with the available context, do that. A planner-ready request should pass through unchanged.
Decision
| Input | Action |
|---|---|
| Clear goal, deliverable, scope, and success condition | passthrough |
| Clear goal or several clear deliverables with handoff-blocking gaps | refined |
| One requested outcome has multiple incompatible interpretations | ask |
Ask at most three questions and only when the answer changes the deliverable, permission boundary, or workflow. Do not manufacture file paths, deadlines, features, risk decisions, or acceptance criteria.
Refinement method
- Identify the requested outcome and next consumer.
- Separate distinct deliverables instead of choosing one silently.
- Preserve explicit constraints, exclusions, permissions, and prior decisions.
- Add only the minimum output shape and success condition required by the next consumer.
- Mark unresolved inputs with
<NEEDS: ...>. - Keep the original request verbatim in the output.
Several explicit deliverables are not an ambiguous goal. Preserve each as a
separate workstream, state their scope boundary, and mark priority/dependency
questions with <NEEDS: ...>; use action: refined. Use ask only when the
requested outcome itself cannot be normalized without choosing incompatible
meanings on the user's behalf.
For migrations, destructive operations, credential changes, or other hard-to- reverse work, do not choose a workflow mode. Surface missing rollback, backup, approval, and recovery inputs when they materially affect whether the next agent can plan safely.
What ships with it
3 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.
- 1mo ago First seen · 139 lines · 73 tokens per session scan A 52f034232908
mastermind-prompt-refiner is a skill published in the GitHub repository xcrft/mastermind (13 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 986 once invoked, about $0.0003 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
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
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…
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…
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.
prompt-library-for-startups
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock…