What is reading-research-overviews?

A way to read and explain the results of an AI co-scientist session, including its overview, ranked hypotheses, reviews, and match history. Its Elo scores show a within-session preference order, not the probability that an idea is correct.

It is for understanding what a research session found, examining its leading hypotheses, explaining their ratings, and summarising the final overview.

It prevents conclusions from being drawn from rankings alone and puts the debates, reviews, and synthesis into context.

reading-research-overviews — Skill by Ahmad-Jaradat-Space

Install

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.

Any agent

npx skills add Ahmad-Jaradat-Space/co-scientist-plugin --skill reading-research-overviews

Clone the repo

git clone --depth 1 https://github.com/Ahmad-Jaradat-Space/co-scientist-plugin

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ahmad-jaradat-space/co-scientist-plugin/reading-research-overviews/github.svg)](https://agentmods.dev/skills/ahmad-jaradat-space/co-scientist-plugin/reading-research-overviews)

Your own site

<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.

Your own site · 80×15

<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>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,019 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00037	$0.00408
Sonnet 5.5	$0.00019	$0.00204
Haiku 4.5	$0.00009	$0.00102

Measured 2mo ago against content hash 4887c3cdae87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

skills/reading-research-overviews/SKILL.md · 98 lines

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_status to confirm the session finished and see matches_played and elo.
co-scientist:overview_get for the meta-review synthesis. This is the headline output.
co-scientist:hypotheses_list for the ranking.
co-scientist:hypothesis_get for 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_played before 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: disproved or other_more_likely outranks 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.

Read the full file on GitHub · 98 lines

Changes

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 · 98 lines · 93 tokens per session scan A 4887c3cdae87

Subscribe to this mod's changes

reading-research-overviews 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 93 tokens to every session and 1,019 once invoked, about $0.0004 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.

Claude Code Research Scientific agent-plugins agent-skills ai-agents codex hypothesis-generation

reading-research-overviews next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reading-research-overviewsAhmad-Jaradat-Space/co-scientist-plugin	Skill	1	2mo ago	Apache-2.0	A	93	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