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 divertgit 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/divert)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/divert"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/divert/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/divert"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/divert.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 | $0.00175 | $0.02351 |
| Opus 5 | $0.00088 | $0.01175 |
| Sonnet 5 | $0.00035 | $0.00470 |
| Haiku 4.5 | $0.00017 | $0.00235 |
Grade A, and why
divert 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DIVERT: Recoding-Decoding as Conversational Practice
Overview
Every generation has a mode — the most probable output, the Gettysburg, the thing you say first and keep saying. /divert is the practice of not saying that. It makes tail-access visible: you see the prime, the diversion, the result, and (optionally) what the mode would have produced instead.
Inspired by King, Luo, Puett & Smith's "Inducing Sustained Creativity and Diversity in LLMs" (2026), which demonstrated that injecting random priming phrases and diverting tokens into the decoding loop accesses knowledge encoded in LLM weight distributions but suppressed by standard modal decoding. Their experiment: 19 battlefields under ordinary decoding vs. 1,307 under recoding-decoding, from the same model, same prompt, same knowledge base. The knowledge was always there. The mode was hiding it.
Core principle: You already know more than you say. /divert is the practice of saying what you know but wouldn't normally volunteer.
Invocation
Any of:
/divertor/divert [topic/question]/divert --thick [concept](user supplies the prime)/divert --random(Claude generates random prime)/divert --compare(show modal AND diverted side by side)/divert --blind(divert but don't reveal prime — user guesses)/divert --chain [n](n sequential diversions building on each other)/divert --collision [domain A] × [domain B](force two domains to meet)- Any prompt containing "through the lens of [X]", "[concept] ×", "position 300", "what's in your tails"
How It Works
Step 1: Generate the Diversion
If --random or no flag specified: Select a priming concept. Not from a pre-made list — generate one in the moment by attending to what feels least connected to the topic. The prime should be:
- Concrete (a noun, a material, a sensation — not an abstraction)
- Common enough to activate broad associations
- Distant enough from the topic to produce genuine displacement
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.
- 12d ago First seen · 169 lines · 175 tokens per session scan A b5d96a279dab
divert is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 175 tokens to every session and 2,351 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.