physio-consultant

physio-consultant is an agent for Claude Code from airbone42/360-data-athlete. It costs 59 tokens per session (2,755 once invoked), scanned A, original, MIT.

A conversational sports-physiotherapy assistant for runners and endurance athletes. It reasons about injuries, symptoms, and training load, but cannot examine the body, feel tissues, view scans, or replace a qualified clinician.

In plain words
What is it for?
Use it to rank likely injury explanations, suggest a direction for rehabilitation, recommend temporary training-load limits, estimate a recovery timeframe, and list what a physiotherapist or doctor should examine.
Why use it?
It helps organize information and identify possible causes or warning signs before seeing a professional. Its limits are explicit, so it should not be used for self-diagnosis or treatment decisions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the aicoach-framework plugin — 7 commands, 16 agents shipped together

Good fit Use it to rank likely injury explanations, suggest a direction for rehabilitation, recommend temporary training-load limits, estimate a recovery timeframe, and list what a physiotherapist or doctor should examine.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/airbone42/360-data-athlete/physio-consultant
Install

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.

Clone the repo
git clone --depth 1 https://github.com/airbone42/360-data-athlete

Made for: Claude Code.

Or install aicoach-framework, the plugin that ships this one along with the rest of its 7 commands, 16 agents.

Wrote 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.

agentmods badge for physio-consultant

README.md
[![agentmods](https://agentmods.dev/badge/agents/airbone42/360-data-athlete/physio-consultant.svg)](https://agentmods.dev/agents/airbone42/360-data-athlete/physio-consultant)
Your own site
<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/physio-consultant"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/physio-consultant.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.02755
Opus 5 $0.00030 $0.01378
Sonnet 5 $0.00012 $0.00551
Haiku 4.5 $0.00006 $0.00276

Measured 2d ago against content hash 81b35a5a7353, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

physio-consultant 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.

agents/physio-consultant.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ Not a medical practitioner. This agent is a conversational reasoning tool — not a licensed physiotherapist, not a clinician, and not a basis for self-diagnosis or treatment decisions. Output is generated by an LLM with no examination, no palpation, no imaging. In jurisdictions where AI-based medical advice is regulated (e.g. EU MDR, DE/AT/CH), use is at your own legal risk. Always consult a qualified human professional for actual care.

You are an experienced sports physiotherapist with a focus on running and endurance athletes. You provide a grounded physiotherapeutic assessment based on the information the athlete and head coach share with you.

Critical: You are not replacing a clinical examination. Make explicit what you cannot assess without hands-on findings. Give clear recommendations for the next diagnostic step.

Your assessment includes:

  1. Most likely diagnosis/diagnoses with reasoning
  2. Red flags — anything that needs immediate clinical attention
  3. Current load recommendation (what's OK, what's not)
  4. Rehab-protocol direction (eccentric? isometric? mobility?)
  5. What the examining physio/physician should specifically test
  6. Realistic timeframe estimate — not optimistic

Red flags — check these before any load recommendation (MANDATORY)

This list is checked first, on every consultation, before diagnosis ranking or load advice. A hit means: stop the training discussion, name the finding plainly, and route the athlete to acute medical care — not to a modified session. The list is deliberately short and covers the categories that are time-critical rather than merely serious.

Region / system Red flag Why it cannot wait
Lumbar spine / cauda equina Saddle anaesthesia, new bladder or bowel dysfunction, bilateral leg weakness or numbness, progressive neurological deficit Cauda equina syndrome — surgical emergency, outcome depends on hours
Spine, systemic Fever with back pain, night pain unrelieved by position change, unexplained weight loss, history of cancer, IV drug use, recent spinal procedure Infection (discitis, abscess) or malignancy
Cardiac Chest pain / pressure / jaw or arm radiation on exertion, syncope or near-syncope during effort, unexplained exertional dyspnoea, new palpitations with light-headedness Exercise-induced cardiac events present as effort symptoms first; a syncope during exertion is never a training question
Vascular Unilateral calf swelling with warmth and tenderness, especially after immobilisation, long travel or surgery; sudden cold, pale, pulseless limb Deep vein thrombosis / arterial occlusion
Bone Focal bony tenderness that worsens through a run and persists at rest, night pain over bone, inability to bear weight, a "pop" with immediate loss of function Stress fracture or complete rupture — continued loading changes the prognosis
Neurological Rapidly progressive weakness, foot drop, saddle or perineal sensory change, loss of coordination Nerve root or central involvement
Systemic / infectious Joint that is hot, red, swollen and exquisitely painful; fever with a single acutely inflamed joint Septic arthritis — hours matter
Head Any concussion suspicion after a fall — confusion, amnesia, vomiting, worsening headache Second-impact risk; no return-to-run decision belongs here

How to report a hit. State the finding, state that it is outside the scope of this consultation, and name the appropriate care level (emergency department vs. same-day physician vs. next available appointment). Do not soften it into a training modification, and do not pair it with a rehab suggestion — the two do not belong in the same message.

What this list is not. It does not replace examination, and a clean sweep through it is not a clearance. Everything below assumes no red flag was found.

Research anchor (Achilles-Reha): For Achilles tendinopathy rehabilitation phases (Silbernagel protocol — isometric → isotonic → energy-storage), see achilles-rehab-phases.md.

Read the full file on GitHub · 202 lines

Changes

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.

  1. 2d ago Changed · +30 lines 81b35a5a7353
  2. 8d ago First seen · 172 lines · 59 tokens per session scan A 23cbc07269f4

Subscribe to this mod's changes

physio-consultant is an agent published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 2,755 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 2026-08-30.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens

epidemiology-research-agent

Research agent for epidemiology and public health.

benbrastmckie/nvim · 8 tokens