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 eductiogit 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/eductio)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/eductio"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/eductio/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/eductio"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/eductio.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 | $0.00218 | $0.02045 |
| Opus 5 | $0.00109 | $0.01022 |
| Sonnet 5 | $0.00044 | $0.00409 |
| Haiku 4.5 | $0.00022 | $0.00204 |
Grade A, and why
eductio 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eductio
A diagnostic lens, not a doctrine. The Scholastics built precise machinery for asking where new forms come from; this skill ports that machinery to any domain where the question recurs. Run the moves below as a menu, not a form to fill out. The lens works equally for the naturalist and the scholastic — it clarifies what each position must claim, without deciding between them.
The Distinction
Eduction (educere, to lead out): the agent actualizes a form already lying in the patient's potency. Fire heats wood; the wood's own capacity for heat is drawn into act. The agent occasions; the patient supplies.
Induction: the agent imposes a form the patient does not contain. The builder orders bricks into a house; brick-nature contains no house. The form arrives from the agent's side.
The real criterion — state it early, because everything depends on it: the question is never where the form comes from but whether the form exceeds the recipient's subjective potency. Origin-talk misleads; capacity-talk decides. Any analysis that argues about the agent before auditing the patient has started at the wrong end.
The Three Potencies
Audit the patient with this triple distinction. Most confusions in emergence debates are equivocations between these three.
- Subjective potency: determinate capacities of an existing nature. Wood can burn; clay can take a vase's shape; a student who knows arithmetic can be led to algebra. Natural agents act only here.
- Obediential potency: a real aptness of the patient keyed to an agent above its nature — receptivity without containment. The concept exists to thread a needle: it lets a form arrive from beyond the patient's nature without making the patient a mere container, preserving the unity of the result. Wherever you see "X couldn't have produced this, yet the result is genuinely X's," suspect obediential potency is being claimed, openly or not.
- Objective potency: bare possibility, anchored in no existing subject at all. The domain of creation proper, or — translated — of initial conditions. Nothing is educed from objective potency; it is the limit-case where the eduction/induction distinction itself gives out.
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 · 70 lines · 218 tokens per session scan A c4c422062e7e
eductio is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 218 tokens to every session and 2,045 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
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.