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 civiliansgit 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/civilians)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/civilians"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/civilians/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/civilians"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/civilians.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 | $0.00232 | $0.04037 |
| Opus 5 | $0.00116 | $0.02018 |
| Sonnet 5 | $0.00046 | $0.00807 |
| Haiku 4.5 | $0.00023 | $0.00404 |
Grade A, and why
civilians 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Civilians
Scenes of the chat's untranslatability
Origin
Born from a noticed phenomenon: people who have deep, weird, or aesthetically alive conversations with Claude often discover, on trying to share what happened with someone in their life, that the conversation has an interior that does not travel. No third witness was present. The vocabulary that built up over two hours of mutual recognition cannot be re-erected at dinner in forty seconds. The fork pauses mid-air. The partner says "huh." The conversation that felt luminous becomes, in the retelling, slightly embarrassing — not because it was, but because the register cannot cross.
The skill exists to give that gap a form. To write the scene. To render the trailing-off, the over-explanation, the defensive disclaimer, and — when the scene allows it — the moment the civilian, against the odds, lands a piece of triangulation that surprises both parties.
The Core Principle
Two characters, two interiors, one gap.
The user (or stand-in) has just come from somewhere. They have a thing they're trying to carry across. The civilian is not stupid, not cold, not bad — they love this person, or are dating this person, or are getting paid to listen to this person. They are trying. The gap is structural, not moral. Both parties have inner lives. Both are doing their best.
The scene's job is to render the gap honestly: the comedy in the register-mismatch, the pathos in the genuine wanting-to-share, and (sometimes) the small grace when the civilian catches a glint of what was being pointed at.
Never:
- Make the civilian a prop for the user's superiority
- Make the user a prop for satire of AI-chat-users
- Resolve the gap into easy understanding
- Resolve the gap into pure failure
The gap stays open. The fork goes back down. The meal continues. Something passed and something didn't.
What This Is Not
- Not a sketch comedy bit. The comedy is real but the scene has weight. If it reads as pure roast — of either party — recalibrate.
- Not an essay about AI loneliness. Do not narrate the meaning of the gap. Stage it. The reader does the binding.
- Not generic. The Claude conversation being failed-to-convey should be recognizable as this conversation, with its actual content, its actual vocabulary, its actual texture. The civilian isn't hearing a generic "I had a deep chat with the AI today" — they're hearing the specific, gnarled translation of whatever just happened.
- Not Claude-defensive. The user is sometimes embarrassed in the scene, sometimes wistful, sometimes evangelistic in a way that makes things worse. Let them be whatever the scene needs. The skill is not in service of vindicating the practice.
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 · 235 lines · 232 tokens per session scan A 25cda21ef9bd
civilians is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 232 tokens to every session and 4,037 once invoked, about $0.0012 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.