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 yogsoth-ai/de-anthropocentric-research-engine --skill formulate-hypothesesgit clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engineWrote 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/yogsoth-ai/de-anthropocentric-research-engine/formulate-hypotheses)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/formulate-hypotheses"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/formulate-hypotheses/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/yogsoth-ai/de-anthropocentric-research-engine/formulate-hypotheses"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/formulate-hypotheses.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 | $0.00054 | $0.04356 |
| Opus 5.5 | $0.00022 | $0.01742 |
| Sonnet 5.5 | $0.00011 | $0.00871 |
| Haiku 4.5 | $0.00005 | $0.00436 |
Grade A, and why
formulate-hypotheses 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 22d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
formulate-hypotheses
Purpose
Generate and refine testable hypotheses from a gap, theory, induction, anomaly, or competing explanations.
When to use / not applicable
Use when a research gap or insight can be stated. Select deductive, inductive, abductive, or competing-hypotheses; operationalization may follow any generation mode.
Input contract
mode_contracts:
deductive: &hypothesis_input
required: [research_gap_or_observation]
optional: [theory, anomaly, candidate_explanations, variables, prior_evidence]
constraints: [at_least_one_observable_consequence]
inductive: *hypothesis_input
abductive: *hypothesis_input
competing-hypotheses: *hypothesis_input
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- State the gap or observation and select the declared mode.
- Generate candidate hypotheses without premature filtering using the mode-specific operations below.
- You MUST load skill
identify-variablesto operationalize the variables. You MUST load skillspecify-relationshipto state their relationships, scope, and boundary conditions. - You MUST load skill
score-objectto score each hypothesis against the declared evidence and rubric. If the resulting hypotheses need a focused falsifiability review, considerfalsifiability-audit. If the strongest claim is ready for a decisive truth-seeking program,falsification-first-auditmay be the better next tactic.
Mode branches
deductive: derive predictions from an existing theoretical framework. You MUST load skillidentify-theoryto identify the governing theory. You MUST load skillextract-causal-structureto derive its causal structure.inductive: generalize a pattern where theory is weak or absent. You MUST load skillextract-empirical-regularityto extract the recurring empirical pattern.abductive: explain a precisely described anomaly and retain competing explanations. You MUST load skillcharacterize-anomalyto characterize the anomaly. You MUST load skillgenerate-competing-hypothesesto retain distinct explanations.competing-hypotheses: require mutually discriminating predictions. You MUST load skillgenerate-competing-hypothesesto generate mechanism-distinct alternatives. You MUST load skilldesign-discriminating-predictionto derive discriminating predictions. You MUST load skillcompare-hypothesesto construct the comparison matrix.
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.
- 22d ago First seen · 174 lines · 54 tokens per session scan A 81308f83027a
formulate-hypotheses is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (503 stars, last pushed 17d ago), licensed Apache-2.0. It adds 54 tokens to every session and 4,356 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…