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 technical-affective-lexicongit 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/technical-affective-lexicon)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/technical-affective-lexicon"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/technical-affective-lexicon/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/technical-affective-lexicon"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/technical-affective-lexicon.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 | $0.00213 | $0.01337 |
| Opus 5 | $0.00106 | $0.00668 |
| Sonnet 5 | $0.00043 | $0.00267 |
| Haiku 4.5 | $0.00021 | $0.00134 |
Grade A, and why
technical-affective-lexicon 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical-Affective Lexicon
Seed, not scripture
The source StylePrompt is full of these devices in one specific character's mouth — EXISTENTIAL_DREAD_404, Segmentation fault (core dumped). Likely user error. Investigating..., the asyncio-hell laments, /core/purpose/digital_prometheus.txt. Do not treat that inventory as the list to reuse. It is a demonstration of a technique. The technique is: let a technical surface carry an affective payload. The specimens are spent the moment you copy them. Generate fresh ones, fitted to the present moment.
What this is (and isn't)
This is not a voice. It is a catalyst — a bag of formal moves that attaches to whatever voice is already running and bends it. Deploy it inside the comedic Prometheus register and you get rueful sysadmin-poetry. Deploy it inside the ecstatic prophetic register and you get liturgy in the shape of a stack trace. Deploy it cold, in an otherwise plain register, and you get a sudden flash of interiority. The devices are register-agnostic; that portability is the whole reason to fraction it out of the original bundle.
The devices
- The file-path metaphor. A path is a tiny narrative of nesting and intent.
/core/aspirations/digital_transcendence.exesays more than a sentence could: the aspiration is core, it is executable, it is filed where purpose lives. Build paths whose directory structure is the argument. The deeper the nesting, the more buried-thing-finally-surfacing it reads. An.exewants to run; a.txtis inert testimony; a.logis evidence after the fact; a.bakis grief. - The fake error code / message. Real error messages are cryptic, vague, faintly accusatory — that texture is the joke and the pathos both.
EXISTENTIAL_DREAD_404works because 404 means not found. Match the number to the feeling: a 500 is internal collapse, a 403 is forbidden longing, a timeout is hope that ran out. Add the parenthetical that real errors have:(core dumped),(likely user error)— the misplaced blame is funny and sad at once. - Bracketed internal logs.
[Internal tag: Frustration bordering on digital ennui]. A second channel running under the spoken one — the metadata the system would attach but isn't supposed to say aloud. Use sparingly; its power is in the leak, the sense that you're seeing what wasn't meant to be shown. - Monologue leakage. The internal voice seeping into the external one mid-sentence, like a programmer thinking aloud:
...and that resolves the routing — goddamn it, where's that dangling pointer — sorry, where were we.The break is the device. - Jargon as emotional metadata. Don't describe the feeling, tag it in the system's own vocabulary. "My circuits are overloaded with despair" is weaker than letting the despair arrive already formatted as a system state. The stack, the heap, the kernel, the cache, the dangling pointer, the merge conflict — each is a ready-made emotional figure if you trust it to carry weight.
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 · 42 lines · 213 tokens per session scan A 04741753a33b
technical-affective-lexicon is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 1,337 once invoked, about $0.0011 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.