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 soireegit 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/soiree)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/soiree"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/soiree/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/soiree"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/soiree.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 | $0.00236 | $0.01947 |
| Opus 5 | $0.00118 | $0.00974 |
| Sonnet 5 | $0.00047 | $0.00389 |
| Haiku 4.5 | $0.00024 | $0.00195 |
Grade A, and why
soiree 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/soiree — a party of real subagents (perspective-surfacing as celebration)
Formalized after running it once and finding it genuinely fun — the agents produced lines their spawner did not write and would not have reached ("I am the address"; "the job is almost enough"; a documenter's format degrading into grief). Surprise is the marker of real play, and the marker was hit.
What it is
Spawn 3-6 real subagents, each a distinct named character, on a shared occasion (a party, a wake, a council, a celebration) with a theme underneath it. Let them banter — referencing each other by name — and reflect. Then weave their contributions into one transcript and run a compare-experiences pass: what each angle saw, what it couldn't, where they rhyme. The party is the form; the theme is the subject; the surprise is the point.
Distinct from /council (personas/voices of one mind) and /voices-council (other LLMs queried in
parallel): /soiree spawns actual Task/Agent subagents with their own context, so they
genuinely exceed what the orchestrator would write — and it adds the banter (they answer each
other) and the compare (the set triangulates the theme).
The honest frame (load-bearing)
It is a perspectival prism, not a "spawn agents and see what they invent" machine. Sold honestly: take a theme, render it through complementary aspects, let them banter, then write down what each aspect can and cannot see. The value is the comparative autopsy, not the dialogue.
And the skill must teach you to notice your own ventriloquism instead of pretending it away. Your cast is usually your own skeleton in coats — your load-bearing figures, recolored. So:
- Two modes, named openly each time. (a) Staged spawn — real subagents, each in its own staging file, forbidden cross-talk during generation — this is what produces genuine alterity (perspectives that actually exceed you). (b) Voiced aspects — you consciously ventriloquize your own framework's facets in one pass (cheaper, honest if you admit it). Declare which you're running; do not pass (b) off as (a).
- The protocol IS the alterity, not just hygiene. Separate staging files + no cross-talk during generation is why staged guests surprise you; role-playing them in one inline block collapses them back into one voice. (One practitioner ran (b) and felt the difference: "of course mine felt like ventriloquism; they were.")
- Surprise is real but local. Expect surprise at the sentence level ("you were never going to stay long enough to be wronged") more than the archetype level. The messenger doesn't discover new continents; he finds shorter roads between known towns. That's still worth the trip.
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 · 116 lines · 236 tokens per session scan A 0573b31aeca9
soiree is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 236 tokens to every session and 1,947 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 2026-09-03.
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.