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.
git clone --depth 1 https://github.com/poemswe/co-researcherWrote 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/plugins/poemswe/co-researcher/gemini-extension)<a href="https://agentmods.dev/plugins/poemswe/co-researcher/gemini-extension"><img src="https://agentmods.dev/badge/plugins/poemswe/co-researcher/gemini-extension/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/plugins/poemswe/co-researcher/gemini-extension"><img src="https://agentmods.dev/badge/plugins/poemswe/co-researcher/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
co-researcher 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 today.
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.
What it actually says
{
"name": "co-researcher",
"version": "2.9.0",
"description": "Academic research extension for Gemini CLI: literature reviews, systematic reviews, peer review and citation checking, with every citation verified against OpenAlex, arXiv and Europe PMC",
"author": "poemswe",
"license": "MIT",
"repository": "https://github.com/poemswe/co-researcher",
"commands": {
"directory": "commands"
},
"context": "GEMINI.md"
}What ships with it
3 files beside gemini-extension.json 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.
- today Changed 04e188b92d78
- yesterday Changed 97bcaab9a696
- 3d ago Changed 2cea82c5cd29
- 6d ago Changed f062094be33c
- 10d ago Changed 8b47babd0282
- 1mo ago First seen · 12 lines scan A 6c435ebaf843
co-researcher is a plugin published in the GitHub repository poemswe/co-researcher (131 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
paper-submission
The post-draft lifecycle nobody else covers: CFP requirement parsing, venue/track selection and tailoring, desk-reject preflight, anonymization, review triage, benchmark scorecards, rebuttals in all three real formats, and camera-ready rails for ACM and IEEE.
paper-writing
Venue-aware academic writing: reflection passes, abstracts, related work, literature reviews, prose polish, and author/venue style matching grounded in verified citations.
paper-search
Key-free scholarly search and legal open-access fetching: DBLP, Crossref, Semantic Scholar, arXiv, Unpaywall — plus citation verification and exemplar study.
paper-presenting
From accepted paper to the podium: slide decks, talk scripts timed to the exact slot, Q&A rehearsal, and venue-sized posters.
aej-macroeconomics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Macroeconomics (AEJ: Macro) — the American Economic Association's quarterly journal for broad-interest macroeconomics, covering growth, business cycles, monetary and fiscal policy, labor-macro, international macro, and macro-finance. The pack.
asplos-skills
A 12-skill depth pack for ASPLOS submissions: cross-layer venue fit, the two-deadline HotCRP cycle, rapid review and rebuttal strategy, Major Revision handling, camera-ready, ACM artifact badges, hardware-evaluation reproducibility, supplementary appendices, writing style, related work, experiments, and workflow.…