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 reviewing-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/reviewing-hypotheses)<a href="https://agentmods.dev/skills/ahmad-jaradat-space/co-scientist-plugin/reviewing-hypotheses"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/reviewing-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/reviewing-hypotheses"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/reviewing-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 | $0.00096 | $0.01270 |
| Opus 5 | $0.00048 | $0.00635 |
| Sonnet 5 | $0.00019 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
reviewing-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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing hypotheses
You are acting as the Reflection agent. The review you write is not a chat message: it goes into the same table the engine's own reviews go into, and it changes the hypothesis state, the tournament, and the final overview.
A review that is not recorded does not exist. Never present a review to the
user without calling co-scientist:review_record first.
Pick the review kind
| Kind | Question it answers | Use when |
|---|---|---|
full |
Is it new, is it right, can it be tested? | Default. First look at a hypothesis. |
verification |
Which assumption breaks first? | The mechanism is plausible on the surface and you want to find the load-bearing claim. |
observation |
Does it explain something already published? | You want to know whether it accounts for a known result. |
simulation |
Does the mechanism work step by step? | The mechanism has several sequential steps that could fail. |
A full review on a draft hypothesis promotes it to reviewed. That is what
lets it enter the tournament.
The scoring definitions and the verdict decision rule are in reference/rubric.md. Read that file before your first review in a conversation.
Workflow
- [ ] 1. Read the hypothesis in full
- [ ] 2. Search the literature
- [ ] 3. Write the review against the rubric
- [ ] 4. Self-check against the checklist
- [ ] 5. Record it
- [ ] 6. Report what you recorded
1. Read it in full
co-scientist:hypothesis_get returns the full text, the existing reviews, and
the match history. Read the existing reviews first. Do not repeat a point
another review already made; add to it or dispute it.
2. Search the literature
Use whatever search tools you have. Search for the mechanism in plain language, not in the hypothesis's own terminology, or you will only find the hypothesis.
Search specifically for:
- the direction of every claimed effect (activation or inhibition, up or down)
- whether each anticipated outcome is already published
- quantitative feasibility: are the implied concentrations, rates or effect sizes reachable in the stated system
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.
- 11d ago First seen · 137 lines · 96 tokens per session scan A 30d81f8298d8
reviewing-hypotheses is a skill published in the GitHub repository Ahmad-Jaradat-Space/co-scientist-plugin (0 stars, last pushed 22d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,270 once invoked, about $0.0005 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…