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 5.5 | $0.00033 | $0.00452 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,131 once invoked, about $0.0003 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 2026-08-31.
ranking-hypotheses compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ranking-hypothesesAhmad-Jaradat-Space/co-scientist-plugin | Skill | 1 | 2mo ago | Apache-2.0 | A | 83 | Claude Code, Codex |
| glycoengineeringK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 183 | Claude Code |
| molecular-dynamicsK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 180 | Claude Code |
| molfeatK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 165 | Claude Code |
| rowanK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 100 | Claude Code |
| depmapK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 128 | Claude Code |
| pytdcK-Dense-AI/drug-discovery-agent-skills | Skill | 54 | 5d ago | MIT | A | 150 | Claude Code |