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 Wondermonger-daydreaming/claude-skills-library --skill recodegit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/recode)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/recode"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/recode/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/wondermonger-daydreaming/claude-skills-library/recode"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/recode.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 | $0.00028 | $0.01952 |
| Opus 5.5 | $0.00011 | $0.00781 |
| Sonnet 5.5 | $0.00006 | $0.00390 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
recode 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recode
Prompt-level recoding-decoding for sustained creativity and diversity
Inspired by Luo, King, Puett & Smith (2025), "Inducing Sustained Creativity and Diversity in Large Language Models." The paper shows that as LLMs improve at accuracy, their probability distributions peak harder around the mode — better models encode MORE knowledge but surface LESS of it. Recoding-Decoding (RD) breaks this trap by injecting random perturbations to push generation into the long tails where unconventional, heterodox, culturally specific knowledge lives.
Since we don't have token-level decoding control, this skill implements RD at the prompt level — validated by the paper's own chat-completion simulation approach (Section 3).
When to Invoke
- Brainstorming where you need genuinely different ideas, not rewordings of the same 5
- Research topic exploration — finding the angle nobody else will find
- Naming things, metaphor-hunting, design space exploration
- Any generative task where you suspect you're getting "the standard AI answer"
- When diversity matters more than correctness
- Literature review ideation — what's the paper nobody cites?
The Algorithm
The paper's RD algorithm (Algorithm 1) uses two forms of randomness:
- Priming phrase — random semantic anchor prepended to the prompt (exploits positional attention bias)
- Diverting token — random 3-letter stem appended to force a specific phonetic/semantic entry point
We adapt this to prompt-level perturbation with five perturbation strategies:
| Strategy | Template | What it does |
|---|---|---|
| Domain prime | Thinking from the perspective of [random discipline]: |
Cross-pollinates from unexpected fields |
| Cultural anchor | Drawing on the traditions of [random culture/region]: |
Breaks Western/anglophone default |
| Temporal displacement | As if answering from [random decade/century]: |
Shifts historical frame |
| Contrarian inversion | The answer most experts would dismiss but a heterodox thinker would defend: |
Targets the anti-mode directly |
| Phonetic seed | Starting from the concept closest to "[random 3-letter stem]": |
Paper's diverting token, adapted |
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 · 175 lines · 28 tokens per session scan A 3e4dbb269bdf
recode is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (7 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 1,952 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
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…
manus-prompt-engineering
Design and audit Manus prompts for engineering, release, production, and security work. Use when writing a Manus prompt or reviewing a Manus execution or recording against authorization and evidence.
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
prompt-forge
Engineers and optimizes prompts for LLMs: system prompts, few-shot examples, chain-of-thought structures, agent personas, and evaluation frameworks. Use this skill when the user wants to write or improve a system prompt, design few-shot examples, create an agent persona, optimize prompt performance, set up prompt…
chief-ai-officer-advisor
Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI Act + US state patchwork, AI cost economics (API-to-self-hosted breakeven), and AI team org evolution. Use when deciding whether to call an API or fine-tune, classifying AI use cases…