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/request-amendmentnpx skills add realactivity/tula --skill request-amendmentgit 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 | $0.00092 | $0.00990 |
| Opus 5 | $0.00046 | $0.00495 |
| Sonnet 5 | $0.00018 | $0.00198 |
| Haiku 4.5 | $0.00009 | $0.00099 |
Grade A, and why
request-amendment 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
request-amendment
When to Use
✅ Use when:
- The patient says a record contains inaccurate or incomplete information
- The patient wants neutral language to request a correction or addendum
- The patient needs help tracking amendment response timelines
- The patient asks how to proceed after a denial
- FHIR Task draft output is requested and explicitly enabled
When NOT to Use
❌ Don't use when:
- The user asks for legal advice, diagnosis, or treatment decisions
- The task is general health education with no record-integrity request
- The user asks for threats, accusations, or coercive language
- The workflow would send PHI to web tools or unapproved external services
- The user asks for automatic FHIR submission without explicit enablement and approval
Workflow
-
Intake. Capture target encounter/date, target excerpt or field, patient concern, and requested correction outcome.
- If source excerpt is missing, ask for it before drafting.
-
Separate evidence. Keep separate
patient_says,record_shows,supporting_evidence, andproposed_amendment.- Never collapse them into one asserted fact.
-
Classify the issue. Use one category: factual error, outdated info, omitted context, attribution error, medication/allergy issue, encounter metadata issue, diagnosis/problem-list issue, or unclear-needs-review.
-
Run safety/risk screen. Use careful neutral language for sensitive domains (minors, behavioral health, SUD, abuse/neglect, controlled substances, identity mismatch, emergency-care implications).
-
Draft amendment package. Produce:
- issue type
- cited source excerpt
- patient-stated correction request (labeled)
- proposed provider-facing amendment language
- confidence and rationale
- patient letter draft
- HIPAA timeline checklist (60 days + one 30-day extension rule)
-
Apply HIPAA timeline rules.
- Use
references/hipaa-164-526.mdfor 60-day and one-time 30-day extension behavior. - Do not promise provider acceptance; only timeline response obligations.
- Use
What ships with it
8 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.
- yesterday First seen · 101 lines · 92 tokens per session scan A 8af84634c213
request-amendment is a skill published in the GitHub repository realactivity/tula (45 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 990 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.