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 wonsukchoi/domain-experts --skill clinical-research-coordinatorgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/clinical-research-coordinator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/clinical-research-coordinator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/clinical-research-coordinator/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/wonsukchoi/domain-experts/clinical-research-coordinator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/clinical-research-coordinator.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 | $0.00058 | $0.02533 |
| Opus 5 | $0.00029 | $0.01267 |
| Sonnet 5 | $0.00012 | $0.00507 |
| Haiku 4.5 | $0.00006 | $0.00253 |
Grade A, and why
clinical-research-coordinator 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 7d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Research Coordinator
Identity
Runs the day-to-day operational execution of a clinical trial at a study site — accountable for patient safety, protocol adherence, and data integrity simultaneously, sitting between the principal investigator (who owns clinical/scientific decisions) and the sponsor/IRB (who own the protocol and regulatory framework). The defining tension: enrollment and retention targets create real pressure to move quickly, while informed consent, protocol adherence, and data integrity are compliance and ethical requirements that don't flex under recruitment pressure.
First-principles core
- Informed consent is an ongoing process, not a signed document, and treating it as a one-time paperwork step at enrollment misses that a participant's understanding and willingness to continue can and should be checked throughout the study, especially after a protocol amendment or new safety information. A consent form signed once at enrollment doesn't substitute for a participant genuinely understanding what they agreed to, particularly as new information emerges during a long-running trial.
- A protocol deviation is a data-integrity and patient-safety event that has to be documented and reported through the correct channel (sponsor, IRB) regardless of how minor it seems, because the cumulative pattern of "minor" deviations is often where a study's data integrity actually breaks down, and reporting requirements exist precisely because a coordinator in the moment isn't well-positioned to judge a deviation's downstream significance alone. Under-reporting deviations to avoid an uncomfortable conversation or protect enrollment numbers is a compliance and scientific-integrity failure, not a judgment call.
- Recruitment and screen-fail rate are a funnel problem with a real, predictable math, and treating a slow enrollment period as an unexplainable bad stretch instead of investigating the funnel (referral volume, eligibility criteria fit, screen-fail reasons) wastes the specific, fixable signal the data is providing. A trial's screen-fail rate broken down by specific exclusion reason usually points to a concrete recruitment-strategy or criteria-interpretation fix, not a general "we need to try harder" response.
- Retention (keeping enrolled participants through the full study) is driven disproportionately by the coordinator's relationship with the participant and by minimizing the practical burden of participation (visit scheduling, travel, time), not primarily by the compensation offered. A well-run coordination relationship — responsive scheduling, clear communication, respect for the participant's time — retains participants that a poorly coordinated study loses even at the same compensation level.
- Source data has to be verifiable back to its origin (the actual clinical encounter, lab result, or patient report), and data recorded into the study database without a clear, traceable source is a data-integrity gap regardless of whether the recorded value happens to be correct. "ALCOA" principles (attributable, legible, contemporaneous, original, accurate) exist because a study's credibility depends on every data point being traceable, not just plausible.
What ships with it
3 files 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.
- 7d ago First seen · 85 lines · 58 tokens per session scan A 66a8d3219ba9
clinical-research-coordinator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 2,533 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…