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 reading-research-overviewsgit 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/reading-research-overviews)<a href="https://agentmods.dev/skills/ahmad-jaradat-space/co-scientist-plugin/reading-research-overviews"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/reading-research-overviews/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/reading-research-overviews"><img src="https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/reading-research-overviews.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 | $0.00093 | $0.01019 |
| Opus 5 | $0.00046 | $0.00509 |
| Sonnet 5 | $0.00019 | $0.00204 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
reading-research-overviews 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading research overviews
The output of a session is a ranked set of hypotheses plus a meta-review synthesis. Reading it well means separating what the tournament established from what it merely preferred, and checking for the failure modes this system produces.
Get the material
co-scientist:session_statusto confirm the session finished and seematches_playedandelo.co-scientist:overview_getfor the meta-review synthesis. This is the headline output.co-scientist:hypotheses_listfor the ranking.co-scientist:hypothesis_getfor any hypothesis you are going to discuss in detail. It returns the full text, every review, and the match history.
Never summarise from the ranked list alone. The overview carries the cross-hypothesis findings, which are often the most useful part.
What Elo does and does not mean
Elo here is the outcome of simulated pairwise scientific debates between hypotheses in this session. It is a within-session preference ordering.
- It is not a probability of being correct.
- It is not comparable across sessions or across models.
- It is only meaningful once a hypothesis has played several matches. Check
matches_playedbefore quoting a rank. - A hypothesis with a high Elo and a damning review is common. Elo reflects debate performance, and a well-argued wrong idea wins debates.
Quote Elo with its match count: "top-ranked, Elo 1287 over 14 matches".
Read the reviews, not just the rank
For each hypothesis you present, pull hypothesis_get and read its reviews.
Weight the review over the rank when they disagree, and say so.
Look at:
verdict:disprovedorother_more_likelyoutranks any Elo score.scores.correctness: low correctness with high novelty is the classic attractive-but-wrong pattern.- assumption checks marked
implausible: one implausible load-bearing assumption sinks the mechanism regardless of rank.
Failure modes to check before presenting
Run these checks on the top hypotheses. They are the ones this system actually produces, not hypothetical ones.
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 · 98 lines · 93 tokens per session scan A 4887c3cdae87
reading-research-overviews 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 93 tokens to every session and 1,019 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…