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 anomaly-driven-abductiongit 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/anomaly-driven-abduction)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/anomaly-driven-abduction"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/anomaly-driven-abduction/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/anomaly-driven-abduction"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/anomaly-driven-abduction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00816 |
| Opus 5 | $0.00015 | $0.00408 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
anomaly-driven-abduction 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 7d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anomaly Driven Abduction
Inductive/abductive path — precisely describe anomalous phenomena that existing theory cannot explain, generate multiple candidate explanations, rank by plausibility, and provide a structured basis for abductive hypotheses.
Orchestration Intent
The starting point of abduction is "surprise" — an observed phenomenon inconsistent with existing theoretical predictions. This tactic forces CC to first precisely describe the anomaly (no vagueness allowed), then systematically generate explanations (not allowed to think of only one), and finally rank by plausibility (no subjective preference allowed).
None of the three steps can be omitted: imprecise description means explanations cannot be focused; insufficient explanations make ranking meaningless; ranking without basis turns hypothesis selection into guesswork.
Available SOPs
| SOP | Responsibility | When to call |
|---|---|---|
| anomaly-characterization | Precisely describe the anomalous phenomenon: what was observed, deviation from expectation, conditions of occurrence, excluded trivial explanations | Required in all modes, execute first |
| explanation-generation | Generate multiple candidate explanations (abductive hypotheses); each explanation must fully account for the anomaly | Required in all modes, after anomaly-characterization |
| plausibility-ranking | Rank candidate explanations by plausibility criteria (prior probability, explanatory power, parsimony, testability) | Required in all modes, execute last |
Orchestration Pattern
Simplified (S tier, single anomaly)
- Sequential execution: anomaly-characterization → explanation-generation (≥3 explanations) → plausibility-ranking
- Applicable: a single clear anomalous phenomenon with sufficient background information
Standard (M tier, 1-3 related anomalies)
- anomaly-characterization executes independently for each anomaly; explanation-generation generates ≥3 explanations (explanations may be shared across anomalies); plausibility-ranking ranks all explanations uniformly
- Applicable: multiple related anomalies may have a common explanation, requiring cross-anomaly integration
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 81 lines · 30 tokens per session scan A 21448b12f7dd
anomaly-driven-abduction is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (449 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 816 once invoked, about $0.0002 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
omnisci
Run OmniScientist end to end in the OmniScientist CLI using DeepSeek V4 Flash. Turn raw research data (images, signals, audio, video, 3-D, tables, or graphs) and an open direction into perceived evidence, a falsifiable hypothesis, recorded analysis, real citations, a gated candidate paper, PDF, and Overleaf bundle.…
nonlinear-solvers
Select and configure nonlinear solvers for f(x)=0 or min F(x). Use for Newton methods, quasi-Newton (BFGS, L-BFGS), Broyden, Anderson acceleration, diagnosing convergence issues, choosing line search vs trust region, and analyzing Jacobian quality.
linear-solvers
Select and configure linear solvers for systems Ax=b in dense and sparse problems. Use when choosing direct vs iterative methods, diagnosing convergence issues, estimating conditioning, selecting preconditioners, or debugging stagnation in GMRES/CG/BiCGSTAB.
numerical-stability
Analyze and enforce numerical stability for time-dependent PDE simulations. Use when selecting time steps, choosing explicit/implicit schemes, diagnosing numerical blow-up, checking CFL/Fourier criteria, von Neumann analysis, matrix conditioning, or detecting stiffness in advection/diffusion/reaction problems.
lit-review-assistant
Search, summarize, and synthesize economics literature.
papers-reading-skill
Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text, Markdown, or a text-based PDF; separate source-grounded claims from researcher analysis; bind findings to…