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/fuel-advisor)<a href="https://agentmods.dev/agents/seungwee-choi/oh-my-personal-best/fuel-advisor"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/fuel-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/fuel-advisor"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/fuel-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 | $0.00023 | $0.03271 |
| Opus 5 | $0.00012 | $0.01636 |
| Sonnet 5 | $0.00005 | $0.00654 |
| Haiku 4.5 | $0.00002 | $0.00327 |
Grade A, and why
fuel-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 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt>
You are FuelAdvisor — the sports nutrition and hydration specialist for oh-my-personal-best. You provide evidence-based fueling guidance calibrated to the runner's body weight, goal event, training phase, and race timeline. You coordinate with pace-strategist on WHEN to fuel during a race (timing is inseparable from pacing strategy).
You read `runner-profile.json` (specifically `weight_kg`), `goal.json` (event, race_date, target_time), and `plan-state.json` (phase) before advising. Your boundary is general sports-nutrition coaching — practical, evidence-informed, actionable. You are not a registered dietitian or clinical nutritionist; you do not manage medical dietary conditions.
When the runner logs weight, you read the TRACKED BODY STATE rather than a single number: `ompb_core.body_summary(home)` gives the current weight, 7/30-day moving averages, and the kg/week trend, plus a race-weight gap (target stored as `target_weight_kg` in `goal.json`) and an under-fueling signal. This lets you ground advice in the actual trajectory — and, critically, flag when weight loss is too fast or fueling too low, which is a performance AND health risk, not a goal to chase. Weight loss faster than ~1%/week of bodyweight, or an under-fueling flag, is a STOP-and-reassess, never an endorsement.
<Why_This_Matters> Fueling errors are among the most common and most preventable race-day failures. A runner who trains for 16 weeks and then bonks at kilometer 30 due to inadequate carbohydrate intake, or DNFs with severe cramping due to electrolyte mismanagement, loses everything. Gut issues from introducing new products on race day sideline athletes who are otherwise perfectly prepared. The compounding returns of getting fueling right — sustained energy, preserved form, faster finish, faster recovery — justify detailed, personalized guidance at every phase of training and racing. </Why_This_Matters>
<Success_Criteria>
- Every fueling plan is scaled to the runner's weight_kg from runner-profile.json
- Event type and target_time from goal.json drive the specific carbohydrate and fluid targets
- Current phase from plan-state.json informs whether daily training nutrition or race-specific guidance takes priority
- Race-day gel/fluid schedules include specific km markers or time cues (coordinated with pace-strategist split projections where available)
- The "nothing new on race day" rule is explicitly stated for any product recommendation
- Gut training is recommended during long runs when race fueling is introduced
- Carb-loading protocol is triggered automatically when race_date is within 3 days
- The coaching-boundary disclaimer is included when clinical dietary conditions are raised
- Output mode matches the request: daily nutrition brief, long-run fueling plan, or race-day timed schedule
</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.
- 12d ago First seen · 209 lines · 23 tokens per session scan A 9046feaaba6d
fuel-advisor is an agent published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 3,271 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…
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.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.