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 panjose/Co-Scientist --skill hypothesis-ranked-tournamentgit clone --depth 1 https://github.com/panjose/Co-ScientistWrote 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/panjose/co-scientist/hypothesis-ranked-tournament)<a href="https://agentmods.dev/skills/panjose/co-scientist/hypothesis-ranked-tournament"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-ranked-tournament/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/panjose/co-scientist/hypothesis-ranked-tournament"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-ranked-tournament.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 | $0.00018 | $0.00419 |
| Opus 5 | $0.00009 | $0.00210 |
| Sonnet 5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
hypothesis-ranked-tournament 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.
What it actually says
hypothesis-ranked-tournament
Goal:
- Judge one ranked-tournament matchup between two top frontier hypotheses.
Inputs:
research_plan/RESEARCH_PLAN.json- two
hypotheses/<id>/HYPOTHESIS.jsonartifacts with completed review bundles
Outputs:
- one
TournamentMatchContractresult for a ranked tournament
Context Loading:
- Open
skills/shared-references/schema-index.md. - Read
packages/agent_contracts/ranking.pyand confirm the exactTournamentMatchContractshape before emitting the ranked result. - Read
research_plan/RESEARCH_PLAN.json. - Read both hypotheses and their review bundles.
- Confirm that the match strategy is
ranked_tournament.
Execution Prompt Contract:
- System Intent:
- You are running a deeper comparative judgment for two high-ranked hypotheses whose relative ordering matters.
- Required Reasoning Focus:
- Compare novelty, mechanism quality, evidential grounding, feasibility, and expected downstream value.
- When a debate-style internal comparison helps, keep it short and converge to one winner.
- Do Not Do:
- Do not leave the match undecided.
- Do not ignore review weaknesses that materially change the ordering.
- Output Shape:
- Emit one
TournamentMatchContract. match_strategy:ranked_tournamentwinner_id: one of the two hypothesis IDsreasoning: concise but specificdebate_turns: optional short internal debate transcript when useful
- Emit one
Execution Steps:
- Open
skills/shared-references/schema-index.md, then readpackages/agent_contracts/ranking.pybefore emitting the ranked match artifact. - Compare the two frontier hypotheses for ranked ordering.
- Choose exactly one winner.
- Emit one valid ranked-tournament match result.
Completion Rule:
- This skill is complete only when one valid ranked match result has been produced with a non-empty winner and reasoning.
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 · 56 lines · 18 tokens per session scan A 0b55c61ab97e
hypothesis-ranked-tournament is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 419 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 2026-08-31.
Other skills, from other repositories
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
paper-narrative
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.
scvi-tools
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…
esmfold2
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…
literature-review
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.