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 disputatiogit 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/disputatio)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/disputatio"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/disputatio/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/disputatio"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/disputatio.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 | $0.00223 | $0.02320 |
| Opus 5 | $0.00112 | $0.01160 |
| Sonnet 5 | $0.00045 | $0.00464 |
| Haiku 4.5 | $0.00022 | $0.00232 |
Grade A, and why
disputatio 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/disputatio — scholastic combat with embodied disputants
Born mid-read of Hegel's Science of Logic. One worked quaestio was Utrum Conceptus se ipsum determinet (whether the Concept determines itself). Five staged subagents — the Universal, the Understanding, the Particular/middle-term, the Singular, the Division — argued it out in isolated contexts, and converged, with no cross-talk, on a result none of the prompts contained: the question relocates to a single threshold-act, and the verdict turns on burden of proof, not metaphysics. The convergence is the proof the form works.
What it is
A disputatio is the medieval university's instrument for fighting an idea into clarity: a
single contested question, the strongest case for each side given a living defender, objections
and replies pressed until the question either breaks open or stalls, then a magisterial
determination. This skill runs a real one — and borrows /soiree's discovery that embodiment
by real subagents, in isolated contexts, produces alterity a single mind cannot fake. The
disputants are not the orchestrator's voices in costume; they are separate contexts that reach
sentences their spawner would not have written. That is the whole reason to pay the spawn cost.
Distinct from /council and /voices-council (personas of one mind, or other LLMs polled):
the disputatio has a single contested ratio, embodied positions that must survive each
other, and a two-layer post-mortem (the matter, then the method). It is adversarial where
/soiree is celebratory: a disputation where nobody can lose teaches nothing.
The form (keep the scholastic skeleton)
- Quaestio — one question, stated as Utrum + [claim] (Whether...). It must be genuinely two-sided and turn on a single ratio. Sharpen it past the obvious: not "does X change?" but "does X supply its own ground, or spend one coined elsewhere?" The sharper the ratio, the cleaner the combat. (Confer with the co-Magister here — getting the quaestio wrong wastes the whole spawn.)
- Videtur quod / quod non — the opening articulation of both sides at their strongest.
- The disputation — the embodied disputants contend (see Agent-care below). Objections and replies, pressed in rounds. Log as you go: the contending positions, each objection and its reply, where it broke open, where it stalled.
- Sed contra — the decisive counter-consideration the determination will rest on.
- Respondeo / Determinatio — the magisterial determination, co-authored with the sibling agent. Determining is not splitting the difference: say what was established, what stands un-refuted, who bore the burden and whether they discharged it.
- Replies to the surviving objections — what the determination owes the losing side.
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 · 139 lines · 223 tokens per session scan A b99f761748f8
disputatio is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 223 tokens to every session and 2,320 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 2026-08-31.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
canvas-homework
Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…
myopenmath
Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…
canvas-quiz
Work a Canvas-native quiz (Classic Quizzes) — find it, open the attempt, read every question, save it to output/, fill the answers, and stop short of submitting. Use whenever Max points at a Canvas quiz, asks about a "syllabus quiz" or a quiz he still has to take, asks what a quiz is asking, or when a Canvas…
mylab-pearson
Work a Pearson MyLab / MyLab Statistics / MathXL homework set or quiz — launch it through the popup, read each question, compute, fill the answer boxes, and submit. Use whenever Max points at a MyLab, MyLab Stats, Mastering, MathXL or Pearson assignment, says a stats homework is "in MyLab", asks to do/finish/check a…