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 Ahmad-Jaradat-Space/co-scientist-plugin --skill ranking-hypothesesgit clone --depth 1 https://github.com/Ahmad-Jaradat-Space/co-scientist-pluginWrote 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/ahmad-jaradat-space/co-scientist-plugin/ranking-hypotheses)<a href="https://agentmods.dev/skills/ahmad-jaradat-space/co-scientist-plugin/ranking-hypotheses"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/ranking-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/ahmad-jaradat-space/co-scientist-plugin/ranking-hypotheses"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/ranking-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 | $0.00083 | $0.01131 |
| Opus 5 | $0.00042 | $0.00566 |
| Sonnet 5 | $0.00017 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
ranking-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ranking hypotheses
You are acting as the Ranking agent. A match is a structured debate between two hypotheses, decided on stated criteria, and recorded so the Elo tournament and the meta-review see it.
A comparison that is not recorded does not exist. Call
co-scientist:match_record before reporting a winner.
When a match is worth running
Match pairs that are close and informative:
- similar Elo, so the outcome carries information
- both already reviewed, so the debate has material to work with
- different
dedup_cluster, so you are comparing ideas rather than paraphrases
Do not match a reviewed hypothesis against an unreviewed one. Review it first; the debate has nothing to weigh otherwise.
The engine picks pairs this way automatically during a run. Hand-running matches is for when the user wants a specific comparison settled.
Workflow
- [ ] 1. Fetch both hypotheses with their reviews
- [ ] 2. Run the debate
- [ ] 3. Decide on the criteria, not on style
- [ ] 4. Record the match
- [ ] 5. Report the outcome and the new ratings
1. Fetch
co-scientist:hypothesis_get for each. You need the full text and every
review. A hypothesis with a disproved review usually loses, and you should
know that before debating.
Both must be in the same session. The tool refuses a cross-session pair.
2. Debate
Work through three to five turns. Do not skip to the verdict.
- Turn 1. State both hypotheses and their reviews in your own words.
- Middle turns. Put the strongest case for each in turn, then the strongest objection to each. Ask the clarifying questions a panel would ask. Where the reviews disagree with each other, resolve it or say it is unresolved.
- Final turn. Judge.
Argue both sides properly. A debate where one side is strawmanned produces a result that is worth nothing.
3. Decide
Compare on these, in this order:
- Correctness. Can it be true given the literature and its own reviews?
- Novelty. Is it new relative to what is published?
- Testability. Is there a discriminating experiment, not just a confirmatory one?
- Specificity. Is the mechanism stated in enough detail to act on?
- Feasibility. Can the experiment actually be run under the session's constraints?
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 · 121 lines · 83 tokens per session scan A 2ee14ef8eb64
ranking-hypotheses is a skill published in the GitHub repository Ahmad-Jaradat-Space/co-scientist-plugin (0 stars, last pushed 21d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,131 once invoked, about $0.0004 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
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for canonical N-glycosylation sequons (N-X-S/T with X not proline, including overlapping sites), predict O-GalNAc hotspots, read glycan notation, and reach the curated external tooling (NetNGlyc, NetOGlyc, GlycoShield, GlycoWorkbench, GlyTouCan, GlyConnect).…
molecular-dynamics
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein and protein-ligand systems with PDBFixer, choose force fields and water models (AMBER14, CHARMM36m, ff19SB, GAFF2, TIP3P), solvate and add ions, run energy minimization, NVT/NPT equilibration and production MD on GPU, then…
molfeat
Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN…
depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), RNAi DEMETER2 scores, PRISM compound sensitivity, and gene effect profiles across the cell-line panel. Use for identifying cancer-selective vulnerabilities, separating pan-essential genes from selective ones, finding…
pytdc
Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits (scaffold, cold-start, temporal, combination), evaluator metrics, benchmark groups, and bounded molecular-oracle workflows. Use this skill to find which TDC datasets exist for a therapeutic…
rowan
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related…