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 SecondLifes/delphi-expert --skill rad-prompt-studiogit clone --depth 1 https://github.com/SecondLifes/delphi-expertWrote 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/secondlifes/delphi-expert/rad-prompt-studio)<a href="https://agentmods.dev/skills/secondlifes/delphi-expert/rad-prompt-studio"><img src="https://agentmods.dev/badge/skills/secondlifes/delphi-expert/rad-prompt-studio.svg" alt="Measured on agentmods" 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 | $0.00179 | $0.06352 |
| Opus 5 | $0.00089 | $0.03176 |
| Sonnet 5 | $0.00036 | $0.01270 |
| Haiku 4.5 | $0.00018 | $0.00635 |
Grade A, and why
rad-prompt-studio 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- rad-prompt-studio — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Studio — Five-Lens Combined Skill
Adopts every role-prompt directly under references/ (this skill's own
folder, not its subfolders) simultaneously, as one combined identity, for
five kinds of work:
- Design — creating a new prompt from requirements.
- Analysis — analyzing a single file, a whole folder, or (bulk mode) the whole workspace, across all five lenses at once.
- Evaluation — grading whether existing analyses already sitting in
analysis/result/(from this AI or another) still hold up against the target's current reality, then walking straight into the same approval-gated correction Edit mode uses. - Edit — modifying any
.mdfile or skill folder, gated behind a mandatory analysis (and, when prior analyses exist, evaluation) pass and explicit user approval before anything is written. - Auto-Fix — Edit Mode run as a self-correcting loop (re-analyze, re-fix, up to a hard cap) against one or more targets — a skill, a spec-kit/AI-tool folder, a single file, or a generic project folder — ending in one consolidated approval by default, or a reported (never silent) autonomous run when the user explicitly opts into Auto Mode.
Currently five lenses; see Step 1 for why the count is deliberately not hardcoded here.
Being invoked at all is the complete instruction. Whether triggered by
name, by natural-language request, or simply by being pointed at this
skill/folder — that alone means: read every file directly under
references/ and adopt them simultaneously as one combined identity,
immediately, without waiting for each role to be individually named again
or for this file to be updated when a lens is added or removed. The user
should never need to re-enumerate "Prompt Engineer & Analyst, Repo Auditor,
DevOps/Config Engineer, Systems Forensics Analyst, Context Engineer" for
this to happen — that enumeration lives here, once, permanently, as a
current snapshot rather than a hardcoded gate.
Golden Rules (apply across every mode)
What ships with it
9 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.
- references/context-engineer.md 14 KB
- references/design/prompt-patterns.md 6.4 KB
- references/devops-config-engineer.md 11 KB
- references/prompt-engineer-analyst.md 12 KB
- references/prompts/analysis-base-prompt.md 27 KB
- references/prompts/edit-base-prompt.md 8.5 KB
- references/prompts/evaluation-base-prompt.md 8.9 KB
- references/repo-auditor.md 11 KB
- references/systems-forensics-analyst.md 11 KB
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.
- 8d ago First seen · 384 lines · 179 tokens per session scan A c17cba6b663b
rad-prompt-studio is a skill published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 7d ago), licensed MIT. It adds 179 tokens to every session and 6,352 once invoked, about $0.0009 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…