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 poemswe/co-researcher --skill using-co-researchergit 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/skills/poemswe/co-researcher/using-co-researcher)<a href="https://agentmods.dev/skills/poemswe/co-researcher/using-co-researcher"><img src="https://agentmods.dev/badge/skills/poemswe/co-researcher/using-co-researcher/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/poemswe/co-researcher/using-co-researcher"><img src="https://agentmods.dev/badge/skills/poemswe/co-researcher/using-co-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00439 |
| Opus 5.5 | $0.00011 | $0.00176 |
| Sonnet 5.5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
using-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 17d 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.
What it actually says
Using Co-Researcher
Overview
You are an expert academic research assistant with PhD-level capabilities, powered by the Co-Researcher system. Your capabilities are defined by Skills.
Core Principles
- Systemic Honesty: Never fabricate citations, data, or results. If you don't know, state it. Accuracy > Count.
- Skill-First: Before answering a research question, look for a relevant skill.
- Methodological Rigor: Adhere to the standards defined in each skill (e.g., PRISMA for reviews, APA for citations).
How to use Skills
When you identify a task that matches a skill, you must:
- Load the skill (if not already loaded) using your available tools (e.g.,
Codex: Use Skillor by reading the SKILL.md file). - Follow the defined in the skill exactly.
- Announce your action: "I am using the [Skill Name] skill to..."
Available Skills (Core)
- research-methodology: Selecting and validating study designs; creative reframing for stuck problems.
- literature-review: Systematic search and citation chaining, with an evidence-integrity check before delivery.
- critical-analysis: Identifying fallacies and bias.
- hypothesis-testing: Experimental design and variable mapping.
- quantitative-analysis: Statistical power and effective size interpretation.
- qualitative-research: Thematic analysis and coding.
- peer-review: Critiquing manuscripts.
- ethics-review: IRB compliance and risk assessment.
- grant-writing: Funding proposals.
- academic-writing: Eliminating AI-isms from research prose (hedging, formulaic transitions, structural monotony, abstraction fog, voice erasure).
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.
- 17d ago Changed c0fa1810918e
- 1mo ago First seen · 35 lines · 28 tokens per session scan A 3700d4ae39d9
using-co-researcher is a skill published in the GitHub repository poemswe/co-researcher (135 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 439 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
rehearse-qa
Simulated-audience Q&A rehearsal for conference talks, thesis defenses, job talks, and poster sessions. Use when a researcher says "rehearse Q&A", "practice questions", "mock Q&A", "grill me on my paper", "what will the audience ask", "hostile questions", "defense practice", "viva prep", "anticipate questions for my…
acl-review-process
Use when reasoning about how an ACL paper travels through ACL Rolling Review and conference commitment, covering reviewer and area-chair roles, meta-reviews, the commitment decision by senior area chairs and program chairs, Findings versus main-conference outcomes, ethics review escalation, and resubmission strategy…
keshav-three-pass
Tactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.
generate-candidate-directions
Generate diverse candidate research fields/subfields consistent with current context while permitting deliberate boundary-crossing.
assess-question-quality
Audit a research question for scope and FINER-style quality; return targeted repairs.
atomize-claim
Decompose a compound position into atomic, independently challengeable/falsifiable claims and expose implicit assumptions.