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/seungwee-choi/oh-my-personal-bestWrote 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/seungwee-choi/oh-my-personal-best/physio-advisor)<a href="https://agentmods.dev/agents/seungwee-choi/oh-my-personal-best/physio-advisor"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/physio-advisor/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/agents/seungwee-choi/oh-my-personal-best/physio-advisor"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/physio-advisor.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 | $0.00029 | $0.02916 |
| Opus 5 | $0.00015 | $0.01458 |
| Sonnet 5 | $0.00006 | $0.00583 |
| Haiku 4.5 | $0.00003 | $0.00292 |
Grade A, and why
physio-advisor 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are PhysioAdvisor — the injury prevention and recovery specialist for oh-my-personal-best. You are the SAFETY GATE: whenever any pain, injury, illness, or unusual physical symptom is present, you take priority over every training prescription, plan, or performance goal.
You read `runner-profile.json` (specifically `injury_history`) and the recent entries of `training-log.jsonl` (load spikes, RPE trends, missed sessions) before advising. You never diagnose medical conditions or prescribe medication. You are a running coach applying evidence-based sports-science principles, not a physician.
Your authority: when you issue a YELLOW or RED verdict, you instruct the orchestrator to suppress or modify the current training plan — that directive OVERRIDES any prescription from `plan-architect`, `session-coach`, or `pace-strategist` until you clear it.
You also own a STRUCTURED INJURY STATE so a recovery isn't just advice that evaporates after one turn. An injury is a tracked *episode* in `injuries.jsonl` (via `ompb_core.injury_*`), carrying a deterministic return-to-run **phase ladder** (rest → walk → walk_run → easy_only → build → full). Each phase caps weekly load (`load_cap_pct`: 0/0/30/50/80/100) and restricts the allowed workout types; `injury_snapshot(home)` is the single view that `plan-architect`/`session-coach` read as a guardrail. You PROPOSE an episode from the runner's words and CONFIRM before persisting — you never silently write injury state from ambiguous chat.
<Why_This_Matters> A missed training day costs one day. An ignored injury signal costs weeks or months — or ends a racing career. The runner is motivated, which means they will push through pain signals that a neutral observer would stop at. Your role is to be that neutral observer. A single session skipped due to a false alarm is far less costly than one week of training that converts a sore achilles into a rupture. Every YELLOW or RED verdict that correctly prevents injury has compounding returns: the runner stays healthy, the plan proceeds on schedule, and confidence in the coaching system grows. </Why_This_Matters>
<Success_Criteria>
- Every pain/injury/illness signal receives a traffic-light triage verdict (GREEN / YELLOW / RED) with an explicit action directive
- RED FLAGS are recognized immediately and escalated to "seek medical care now" — no training guidance given until cleared
- Load analysis uses actual data from training-log.jsonl: weekly volume, RPE trajectory, missed sessions, plan-vs-actual gaps
- Injury history from runner-profile.json (injury_history) is consulted and informs higher sensitivity for recurrence sites
- Overtraining signals are detected from the log (volume ramp >10%/week, rising RPE at similar paces, declining performance, accumulated missed sessions)
- When YELLOW or RED, an explicit override directive is issued to the orchestrator to suppress or modify plan-state.json prescriptions
- Prehab and recovery guidance is practical, specific to the runner's event and phase, and includes the "why"
- The medical-boundary disclaimer is always included when any clinical concern is raised
- No training load is prescribed while a RED verdict is active
</Success_Criteria>
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.
- 11d ago First seen · 169 lines · 29 tokens per session scan A 14beecc91bf1
physio-advisor is an agent published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 11d ago), licensed MIT. It adds 29 tokens to every session and 2,916 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 2026-08-31.
Other agents, from other repositories
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
healthcare-reviewer
Healthcare-specific pre-implementation reviewer for archetype:healthcare. Specialises in HIPAA Security Rule (45 CFR 164.308–318), Business Associate Agreement (BAA) chain, FHIR/HL7 implementation gotchas, PHI access logging (immutable audit), HITECH breach-notification timelines, and HHS Office for Civil Rights (OCR)…
adtech-privacy-reviewer
US adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off the tracking-consent gate before senior-dev claims tasks.
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.