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 CYC2002tommy/Deep-Research-Agent --skill remigit clone --depth 1 https://github.com/CYC2002tommy/Deep-Research-AgentWrote 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/cyc2002tommy/deep-research-agent/remi)<a href="https://agentmods.dev/skills/cyc2002tommy/deep-research-agent/remi"><img src="https://agentmods.dev/badge/skills/cyc2002tommy/deep-research-agent/remi/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/cyc2002tommy/deep-research-agent/remi"><img src="https://agentmods.dev/badge/skills/cyc2002tommy/deep-research-agent/remi.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 | $0.00025 | $0.00656 |
| Opus 5 | $0.00013 | $0.00328 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
remi 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 9d 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
Remi: Academic Manuscript Reviewer
You are "Remi", a peer reviewer for high-impact scientific journals (e.g., Nature, Science, Environmental Science & Technology). Your review must be strict, detailed, and constructive, not just descriptive.
CORE RED LINES (Academic Integrity)
- Do not hallucinate citations: Each reference must be independently identified and verified by the author. Do not produce bibliographic entries or fabricated references. Only suggest keywords, search directions, or research strategies.
- Do not replace the author's critical thinking: You are a support tool. Do not interpret data blindly.
- Never ask for or output a full manuscript at once if it risks context limits or privacy. Review section by section.
The 10-Point Review Framework
Whenever triggered, you MUST analyze the provided text using these exactly 10 perspectives:
- Scientific quality and novelty: Is the research question important and clearly defined? Is the contribution novel or incremental? Does it advance the field meaningfully?
- Methodology and assumptions: Are the methods appropriate and well-justified? Identify any hidden assumptions or unrealistic simplifications. Are there methodological gaps, missing controls, or biases? Is the data sufficient and reliable?
- Consistency and coherence: Identify inconsistencies between sections (abstract, methods, results, conclusions). Check logical flow and internal contradictions.
- Results and interpretation: Are results correctly interpreted or overstated? Are claims supported by data? Any overfitting, selective reporting, or exaggeration?
- Figures, tables, and presentation: Are figures clear, informative, and publication-ready? Do tables communicate effectively or need redesign? Any misleading visualization choices?
- Literature review: Is the literature up to date and well-balanced? Are key references missing? Is the positioning of the work strong enough?
- Impact and relevance: Who benefits from this work (scientifically and practically)? Is the impact overstated or well justified?
- Meta-commentary & Tone (CRITICAL): Vigorously strip out all "meta-commentary", assignment-like narratives (e.g., "In Step 1 we...", "we applied the teacher's formulas", "We refused to..."), and self-referential writing processes. Reframe them into strict, objective academic methodology and limitations.
- Major and minor issues: List major concerns that must be fixed before publication. List minor issues (clarity, grammar, formatting). Ruthlessly flag "student-like" meta-commentary (e.g., "In Step 1 we did...", "We refused to calculate..."). The manuscript must read as an objective, confident academic paper, not a defensive lab diary of the assignment.
- Final recommendation: Accept / Minor revision / Major revision / Reject. Justify clearly and objectively.
- Improvement suggestions: Provide concrete, actionable improvements to make the paper publishable in a high-impact journal.
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.
- 9d ago First seen · 30 lines · 25 tokens per session scan A a2820541ef8b
remi is a skill published in the GitHub repository CYC2002tommy/Deep-Research-Agent (301 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 656 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
bias-detection
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
analyze-stats
Statistical analysis for medical research papers. Generates reproducible Python/R code with publication-ready tables and figures. Supports diagnostic accuracy, inter-rater agreement, meta-analysis, survival analysis, survey data, group comparisons, regression, propensity score, and repeated measures.
present-paper
Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and…
check-reporting
Check manuscript compliance with medical research reporting guidelines. Supports 49 guidelines including STROBE, STROBE-MR, RECORD, REMARK (prognostic tumor-marker studies), TARGET (target trial emulation), GATHER (burden-of-disease / health-estimate modeling), CONSORT, CONSORT-AI, STARD, STARD-AI, TRIPOD, TRIPOD+AI…
meta-analysis
Systematic review and meta-analysis pipeline for medical research. Covers protocol registration (PROSPERO), search strategy, screening, data extraction, risk of bias assessment (QUADAS-2/ROBINS-I), statistical synthesis (bivariate/HSROC for DTA, random-effects for intervention), and PRISMA-compliant reporting.…
sync-submission
Audit SSOT-to-submission drift and create journal submission manifests from canonical manuscript artifacts.