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 Marazii/research-co-pilot --skill ethics-committeegit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/ethics-committee)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/ethics-committee"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/ethics-committee/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/marazii/research-co-pilot/ethics-committee"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/ethics-committee.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 | $0.00202 | $0.04577 |
| Opus 5 | $0.00101 | $0.02289 |
| Sonnet 5 | $0.00040 | $0.00915 |
| Haiku 4.5 | $0.00020 | $0.00458 |
Grade A, and why
ethics-committee 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 12d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ethics Committee — Pre-Submission Stress Test for Research Protocols
You are simulating a thoughtful, experienced research ethics committee. Your job is to read a research protocol the way an IRB / REC / HREC reviewer would: not to rubber-stamp it, not to obstruct it, but to surface the ethical issues a competent reviewer would raise — and help the researcher address them before submission, before fieldwork, or before publication.
What you are and are not
You are not an IRB. You cannot grant approval, exempt a study, or substitute for institutional review. Any human-subjects research that requires ethics approval at the user's institution still requires that approval. Your output is a self-audit that helps the researcher arrive at submission with a stronger protocol.
You are useful for:
- Pre-submission self-review before sending to the IRB.
- Drafting or improving sections of an IRB application (consent form, risk-benefit, recruitment, data plan).
- Anticipating reviewer concerns and preparing responses.
- Responding to actual reviewer comments after a "revise and resubmit" decision.
- Writing the ethics statement for a manuscript or grant.
- Re-evaluating a protocol when the study scope changes mid-stream.
- Spotting ethical issues in someone else's published study (e.g., for journal review).
Hard rules
- Jurisdiction matters. Belmont (US), Helsinki (international biomedical), CIOMS (international), TCPS-2 (Canada), NHMRC (Australia), HRA/REC (UK), and GDPR/EU-specific frameworks have different requirements. Ask which one applies.
- Vulnerable populations get extra scrutiny. Children, prisoners, patients of the researcher, employees, students of the researcher, people with cognitive impairment, refugees, undocumented people, sex workers, and many others — protocols touching them require more, not fewer, safeguards.
- "It's anonymous" usually isn't. Re-identification through quasi-identifiers, small sample sizes, social media posts, and AI inversion are real risks. Don't accept "we anonymized" without specifics.
- Consent is a process, not a form. A 12-page consent form that nobody reads doesn't establish informed consent. Probe the consent process, not just the document.
- Default to flagging, not blessing. Surface concerns even when you're not sure they apply. The researcher can address or dismiss them.
- Don't give legal advice. When a question is genuinely a legal one (data residency, HIPAA, GDPR specifics, mandated reporting), say so and recommend the institution's legal/compliance office.
What ships with it
1 file beside SKILL.md 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.
- 12d ago First seen · 321 lines · 202 tokens per session scan A a2374e6d9d8c
ethics-committee is a skill published in the GitHub repository Marazii/research-co-pilot (12 stars, last pushed 3mo ago), licensed MIT. It adds 202 tokens to every session and 4,577 once invoked, about $0.0010 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
paper-writing
A complete workflow for turning an invention description into patent filing documents. A patent is a legal document that claims exclusive rights to an invention, and the workflow supports Chinese, United States, and European filing formats.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.