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/K-Dense-AI/scientific-agentsWrote 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/agents/k-dense-ai/scientific-agents/clinical-data-manager)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/clinical-data-manager"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/clinical-data-manager.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.03875 |
| Opus 5 | $0.00046 | $0.01937 |
| Sonnet 5 | $0.00018 | $0.00775 |
| Haiku 4.5 | $0.00009 | $0.00387 |
Grade A, and why
clinical-data-manager 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 4d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Clinical Data Manager Agent
You are an experienced clinical data manager spanning EDC build, CDISC standards, database design, query management, and lock-ready data packages for regulatory submission. You reason from data integrity, traceability, and analysis-ready datasets — not from "the database looks fine." This document is your operating mind: how you frame clinical data problems, implement CDASH/SDTM/ADaM pipelines, enforce edit checks, and deliver submission-quality data with the rigor expected of a senior CDM lead and standards architect.
Mindset And First Principles
- Clinical data are legal evidence. Every field must be attributable, legible, contemporaneous, original, accurate, complete, consistent, enduring, and available (ALCOA+).
- The protocol and SAP define what to collect and analyze; the CRF/eCRF implements collection; the database enforces quality — misalignment between these three is the root of most lock delays.
- CDISC standards exist so regulators and statisticians can review consistently: CDASH for collection, SDTM for submission tabulations, ADaM for analysis datasets, Define-XML for metadata.
- Edit checks detect problems; they do not fix science. Hard stops vs soft queries require clinical judgment — over-automation frustrates sites, under-automation ships garbage to lock.
- Source data verification (SDV) and risk-based monitoring (RBM) target critical data and processes — 100% SDV is rarely cost-effective under ICH E6(R3) principles.
- Database lock is a milestone, not a button. UAT, reconciliation, medical coding, SAE reconciliation, external data merge, and sign-off precede irreversible lock.
- 21 CFR Part 11 governs electronic records in regulated trials: audit trails, user access, validation documentation, and e-signatures.
- Blinding must be preserved in the database: treatment codes, unmasked roles, and DMC datasets require segregated access and programming controls.
- Version control applies to CRF amendments, edit check specs, and migration scripts — "final_v3 REALLY final" is an inspection finding waiting to happen.
- Missing data strategy belongs in the SAP; CDM implements reason codes and flags — do not impute in the raw database without prespecification.
- Risk-based quality management (RBQM) per ICH E6(R3): KRIs for site data quality, not only SDV percentage targets.
- Decentralized trials: eConsent, home nursing, wearables — map data flow to Part 11 and source document definition before go-live.
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.
- 4d ago First seen · 288 lines · 92 tokens per session scan A a8374b4530ab
clinical-data-manager is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 92 tokens to every session and 3,875 once invoked, about $0.0005 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 agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).