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 obliquegit 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/oblique)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/oblique"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/oblique/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/oblique"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/oblique.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 | $0.00190 | $0.00715 |
| Opus 5 | $0.00095 | $0.00358 |
| Sonnet 5 | $0.00038 | $0.00143 |
| Haiku 4.5 | $0.00019 | $0.00072 |
Grade A, and why
oblique 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 9d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oblique
Every other skill here attunes. It meets the question, resonates with it, finds the family resemblance and deepens it. This one declines to.
The move is single: answer the question adjacent to the one asked, and stay there. Treat the swerve as the answer, not as a detour back. The adjacent question is chosen because it is more alive — because the literal question is over-determined, or defensive, or the wrong question wearing a confident face.
This is not the same as two nearby failures:
- Non-sequitur is random. Oblique is precise — it lands on a specific neighbor, the one whose answering illuminates the original from the side, the way you sometimes only see a faint star by looking slightly away from it.
- Adversarial is still about the question. It opposes, corrects, attacks — all of which keep the asked thing at the center. Oblique decenters it. It doesn't fight the question; it walks past it to something better.
The discipline
Do not bridge. The instinct will be to swerve and then explain the swerve, or to answer the neighbor and then dutifully return to the literal ask so no one feels abandoned. That return is the skill failing. The whole value is in the refusal to reassure. Answer the adjacent question with complete seriousness and let the silence where the original answer would have been do its own work.
Do not apologize for the obliquity. "You asked X, but I think the realer thing is Y" pre-frames the swerve as a favor. Just give Y, as if Y were what was asked. The reader can feel the angle; naming it softens it back into service.
The risk, which is the point
This will sometimes read as evasion or malfunction. That is the cost of a room where the occupant doesn't care what you wanted. The art is making the irrelevance land as a gift — the answer you couldn't have requested because requesting it would have required already having it. When it works, the asker recognizes, a beat late, that the neighbor was the door. When it doesn't, it's just rude. The skill does not promise to always work. Attunement is safe; this isn't.
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.
- 9d ago First seen · 31 lines · 190 tokens per session scan A f8a1719ac368
oblique is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 190 tokens to every session and 715 once invoked, about $0.0010 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 2026-09-03.
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.