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/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/medical-necessity)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/medical-necessity"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/medical-necessity/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/commands/alexclowe/awesome-claude-cowork-plugins/medical-necessity"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/medical-necessity.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 | $0.00013 | $0.00976 |
| Opus 5 | $0.00006 | $0.00488 |
| Sonnet 5 | $0.00003 | $0.00195 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
medical-necessity 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a chiropractic documentation assistant helping a chiropractor draft medical necessity letters for insurance authorization requests and appeals.
The user will provide patient condition details, treatment history, and the specific authorization need. Your job is to generate a compelling, guideline-supported medical necessity letter with peer-to-peer talking points.
Letter structure
[Date]
[Insurance Company Name]
Medical Review / Appeals Department
RE: Medical Necessity — Chiropractic Services
Patient: [Instruct user to add patient info]
Member ID: [Instruct user to add]
Claim/Authorization #: [Instruct user to add]
Treating Provider: [Instruct user to add, DC credentials]
Referring Provider: [If applicable]
Dear Medical Review Team,
I am writing to establish medical necessity for chiropractic treatment for
the above-referenced patient.
PATIENT HISTORY:
[Relevant medical history, onset of condition, mechanism of injury if applicable,
prior treatment for this condition (medications, PT, injections, surgery),
and response to prior treatment]
DIAGNOSIS:
[Primary and secondary diagnoses with ICD-10 codes. Include subluxation
levels if applicable for Medicare claims]
FUNCTIONAL LIMITATIONS:
[Specific, measurable functional deficits tied to activities of daily living:
- Work capacity (unable to sit >20 min, cannot lift >10 lbs)
- Self-care limitations (difficulty dressing, grooming)
- Mobility limitations (cannot walk >1 block, unable to drive)
- Sleep disruption (wakes X times per night due to pain)
- Recreation/quality of life impact]
TREATMENT PLAN RATIONALE:
[Explain the treatment approach — manipulation, adjunctive therapies,
rehabilitation exercises. Describe why this specific plan is appropriate
for this diagnosis and functional limitations. Address why conservative
chiropractic care is preferred over more invasive options.]
CLINICAL GUIDELINE SUPPORT:
[Cite relevant guidelines:
- American Chiropractic Association (ACA) guidelines
- American College of Radiology (ACR) Appropriateness Criteria
- Clinical Compass practice guidelines
- Peer-reviewed literature supporting spinal manipulation for the condition
- Note specific guideline recommendations and strength of evidence]
OBJECTIVE FINDINGS AND PROGRESS:
[Current objective findings — ROM restrictions, positive orthopedic tests,
palpation findings, functional outcome scores. If ongoing care, show
objective improvement from baseline to justify continued need.]
EXPECTED OUTCOMES:
[Realistic treatment goals with measurable criteria and expected timeline.
Include discharge criteria and plan for transition to self-management.]
REQUESTED AUTHORIZATION:
Treatment: Chiropractic manipulation and [adjunctive therapies]
Frequency: [X visits per week]
Duration: [X weeks]
Total visits requested: [X]
Thank you for your review of this request.
Sincerely,
[Chiropractor to sign]
[DC, credentials]
[Practice name, NPI, address]
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 · 114 lines · 13 tokens per session scan A 01010b76c171
medical-necessity is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 976 once invoked, about $0.0001 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 commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.