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 adaptive-pair-selectiongit 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/adaptive-pair-selection)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/adaptive-pair-selection"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/adaptive-pair-selection/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/adaptive-pair-selection"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/adaptive-pair-selection.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 | $0.00027 | $0.00539 |
| Opus 5 | $0.00014 | $0.00269 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
adaptive-pair-selection 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adaptive Pair Selection
Select the next comparison pair by information gain, execute the comparison, update ratings, and check for convergence. Repeats until the ranking stabilizes or the comparison budget is exhausted.
Stages
- Select — pair-selector identifies the pair whose comparison would most reduce uncertainty
- Compare — comparison-executor produces a judgment with confidence and reasoning
- Update — rating-update incorporates the new judgment into the rating model
- Check — convergence-check determines if ranking has stabilized
Loop stages 1-4 until convergence or budget exhaustion.
Available SOPs
| Stage | SOP | Input | Output |
|---|---|---|---|
| Select | pair-selector | current_ratings, comparison_history | next_pairs[] |
| Compare | comparison-executor | pair, context | judgment |
| Update | rating-update | judgment, current_ratings, method | updated_ratings |
| Check | convergence-check | rating_history | converged, stability_score |
Execution Guidance
- Start with high-uncertainty pairs (largest sigma or most uncertain boundary)
- For small N: may complete all pairs in first pass, then focus on inconsistencies
- For large N: prioritize pairs near rank boundaries (positions k and k+1)
- Track comparison count against budget; exit gracefully if budget hit
- Pass full rating_history to convergence-check (not just latest snapshot)
Minimum Yield
- Global ranking + confidence intervals + convergence curve
- Global ranking with confidence intervals for each position
- Convergence curve showing stability score over iterations
- Comparison log with all judgments made
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| comparison-executor | Execute a pairwise comparison between two candidates, producing a judgment with winner, confidence, and reasoning. |
| convergence-check | Evaluate whether the ranking has stabilized by analyzing rating history and computing stability metrics. |
| pair-selector | Select the next comparison pairs that maximize information gain given current ratings and comparison history. |
| rating-update | Incorporate a new judgment into the rating model and return updated ratings for all candidates. |
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.
- 10d ago First seen · 65 lines · 27 tokens per session scan A f7209e8bbb90
adaptive-pair-selection is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (449 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 539 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
literature-review-tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use to ..." for…
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…
paper-fulltext-harvest
Batch download academic paper full-text (PDF/XML) from a list of DOIs. Handles 25 DOI prefixes across 19 publisher families via three layered routes: (1) publisher TDM APIs requiring institutional subscription (Elsevier ScienceDirect, Wiley Online, Springer Nature), (2) Open Access sources (Crossref, Unpaywall…
academic-figure-generation
Generates publication-quality academic figures (framework diagrams, pipeline illustrations, system architectures, method overviews) from a paper's method text and a target caption, using a local PaperBanana multi-agent pipeline (Retriever → Planner → Stylist → Visualizer → Critic).
paper-reading
Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden…