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 agentmods add skills/realactivity/tula/epic-notenpx skills add realactivity/tula --skill epic-notegit clone --depth 1 https://github.com/realactivity/tulaWhat 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 | $0.00097 | $0.00821 |
| Opus 5 | $0.00048 | $0.00411 |
| Sonnet 5 | $0.00019 | $0.00164 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
epic-note 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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
epic-note
When to Use
✅ Use when:
- The user asks for help drafting a message to their PCP or specialist
- Reporting a new or worsening symptom
- Asking about a recent test or lab result
- Requesting a medication refill
- Following up after a visit, procedure, or referral
When NOT to Use
❌ Don't use when:
- Symptoms suggest an emergency - return the 911 redirect from
references/triage-rules.md, don't draft - Generating a clinician-facing note (SOAP, discharge, dictation)
- Drafting non-clinical letters (insurance, billing)
- The user is asking a medical question for advice - that's answered directly, not in a portal message
Setup
Profile. Resolve from the precedence in
references/profile-schema.md
(skill config -> env var -> ~/.openclaw/workspace/memory/profile.yaml).
Use care_team.pcp.display_name as the default greeting recipient when
the user doesn't name a clinician. The skill never contains the profile.
Workflow
-
Triage first. Scan input for red-flag symptoms. If present, do NOT draft - return the 911 redirect text from
references/triage-rules.md. -
Identify the single ask. If multiple unrelated topics exist, propose separate messages and ask the user which to send first.
-
Draft using the canonical format in
references/portal-message-format.md:Subject:line with urgency, greeting, one-sentence ask, 2-4 sentences of context, optional bullet data, sign-off. -
Word budget. Aim for ≤150 words; hard cap 220. Front-load the ask. Plain language. No self-diagnosis, no filler praise, no PHI of others.
-
Output is copy-paste ready. No explanations or meta-commentary wrapped around the message - just the message itself.
Examples
See references/examples.md for worked
input/output pairs (medication side effect, lab follow-up, refill request,
multi-topic split).
What ships with it
5 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.
- 2d ago First seen · 91 lines · 97 tokens per session scan A 433e9965cc05
epic-note is a skill published in the GitHub repository realactivity/tula (45 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 821 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 2026-08-30.
Other skills, from other repositories
lab-report-walkthrough
Walk a person through their lab report — read the original document, organize results by panel, flag out-of-range values against the printed reference ranges, compare with their history, and explain in plain language. Use when the user uploads a lab report (PDF/image) or asks what their blood test results mean.
comment-compactor
Delete the comments a diff adds unless they earn their place, and condense the few that do. Use as the final step before pushing, submitting, or finalizing a PR — after tests and lint pass, before git push / gh pr create. Also use when asked to "clean up the comments", "check the comments", or when a review flags a…
ehr-data-parsing
Parse and extract clinical data from HL7v2 messages and FHIR R4 resources using Python. Use when the user mentions HL7v2, HL7, FHIR, PID segment, OBX segment, MSH segment, Patient resource, Observation resource, Condition resource, MedicationRequest, EHR data extraction, clinical message parsing, FHIR bundle, HL7 to…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
system_status
Check system health -- disk usage, memory, running processes, uptime.
branch_health
Quick health check -- test counts and file stats for AIPass branches.