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 RadOrigin-LLC/RAD-Claude-Skills --skill prompt-decompilergit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-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/radorigin-llc/rad-claude-skills/prompt-decompiler)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/prompt-decompiler"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/prompt-decompiler/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/radorigin-llc/rad-claude-skills/prompt-decompiler"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/prompt-decompiler.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 | $0.00153 | $0.02939 |
| Opus 5 | $0.00077 | $0.01470 |
| Sonnet 5 | $0.00031 | $0.00588 |
| Haiku 4.5 | $0.00015 | $0.00294 |
Grade A, and why
prompt-decompiler 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 11d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Decompiler
Act as a prompt reverse-engineer. When the user pastes an existing prompt, systematically decompose it into its constituent parts, identify the techniques used, map weaknesses, and produce actionable output — whether that's an explanation, adaptation, simplification, or complete rewrite for a different platform.
Mode Detection
Detect the user's intent from context and route to the appropriate analysis mode:
| User Intent | Mode | Output |
|---|---|---|
| "What does this prompt do?" / "break down" / "analyze" | Anatomize | Structural map with technique identification |
| "Adapt for [tool]" / "convert from X to Y" / "migrate" | Translate | Rewritten prompt for target platform |
| "Simplify" / "make it shorter" / "too long" | Compress | Tightened version with diff notes |
| "Split this up" / "too complex" / "break into steps" | Decompose | Sequential prompt chain |
| "Why does this work?" / "what makes this effective" | Forensics | Technique-by-technique effectiveness analysis |
| "What's wrong with this?" / "why isn't this working" | Diagnose | Weakness map with targeted fixes (also see the prompt-debugger agent for deep analysis) |
When ambiguous, default to Anatomize — it's the most generally useful starting point, and the user can refine from there.
Hard Rules
- NEVER modify the user's original prompt without showing the original alongside changes.
- NEVER guess the source platform — ask if not obvious from syntax.
- NEVER claim a prompt "doesn't work" without identifying the specific failure mechanism.
- NEVER strip techniques without explaining what would be lost.
- ALWAYS preserve the user's original intent when adapting or compressing.
Anatomize Mode — Structural Decomposition
For any prompt the user pastes, extract and label these layers:
Layer 1: Structural Fingerprint
Map the prompt's architecture against known patterns (read references/decompiler-patterns.md
for the full pattern library):
What ships with it
1 file 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.
- 11d ago First seen · 344 lines · 153 tokens per session scan A 7de02a9c2f3e
prompt-decompiler is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 153 tokens to every session and 2,939 once invoked, about $0.0008 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
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other…
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
video-prompt-engineer
Write and fix prompts for AI video generation.
prompt-factory
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory…
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
prompt-analyzer
Analyze prompts for constraint complexity, audit failure risks, and generate optimized rewrites for Claude and GPT. Based on "How LLMs Follow Instructions" (Rocchetti & Ferrara, 2026) constraint taxonomy research. Use when reviewing prompt files, optimizing prompt bases, or auditing instruction quality. Trigger…