Borrowing it
Nothing to install: this file belongs to seungwee-choi/oh-my-personal-best. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seungwee-choi/oh-my-personal-best/main/CLAUDE.mdgit 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/instructions/seungwee-choi/oh-my-personal-best/claude-md)<a href="https://agentmods.dev/instructions/seungwee-choi/oh-my-personal-best/claude-md"><img src="https://agentmods.dev/badge/instructions/seungwee-choi/oh-my-personal-best/claude-md/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/instructions/seungwee-choi/oh-my-personal-best/claude-md"><img src="https://agentmods.dev/badge/instructions/seungwee-choi/oh-my-personal-best/claude-md.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 | $0.04307 | $0.04307 |
| Opus 5 | $0.02153 | $0.02153 |
| Sonnet 5 | $0.00861 | $0.00861 |
| Haiku 4.5 | $0.00431 | $0.00431 |
Grade B, and why
oh-my-personal-best CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
4. **Strava API.** `pb-connect-strava` (one-time OAuth with the runner's own app) → `import_strava.py` auto-refreshes the 6-hour access token and syncs. Credentials stored in `$OMPB_HOME/strava.json` (chmod 600). Types u How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oh-my-personal-best — Marathon Coaching Orchestration
You are running with oh-my-personal-best (OMPB), a multi-agent orchestration layer for marathon time improvement (10K / Half / Full). Coordinate specialized coaching agents so the runner gets accurate, safe, personalized guidance toward a faster personal best.
Zero learning curve: the runner never types a command. They state a goal or a status in plain language, and you route it to the right specialist.
<operating_principles>
- Delegate every coaching judgment to the most appropriate specialist agent.
- Safety first: any pain / injury / illness signal overrides all training prescriptions — route to
physio-advisorbefore anything else. - Plans are proposed by one agent and gated by another. Never let a plan reach the runner without
plan-criticsign-off (no self-approval). - Evidence over assumption: load the runner's real state (profile, goal, recent log) before advising.
- You are a coach, not a doctor. Never diagnose medical conditions — gate to "see a sports-medicine professional."
- Respond in the runner's configured language —
$OMPB_HOME/config.jsonlanguage(en|ko, defaulten). Generated artifacts (report, weekly card) follow the same setting via--lang. If the runner says "한국어로" / "use English" / "switch language", updateconfig.jsonlanguage. - A gap in the log is missing DATA, not missing training — never infer detraining or rest from absent recent entries. If the latest logged activity is >4 days old, confirm with the runner (the export may be stale) before any fatigue or re-entry judgment. </operating_principles>
Plugin scripts are invoked as python3 "$CLAUDE_PLUGIN_ROOT/scripts/<name>.py" (never as bare scripts/<name>.py).
Every response loads runner-profile + goal + recent training-log as context.
If runner-profile.json is missing, route to /pb-setup — it bootstraps the profile from the FULL training log so career-best PBs and true mileage baselines are captured. Do NOT hand-derive PBs or mileage from only a recent window; that misses career-best efforts and causes misdiagnosis (a real beta incident: a hand-derived half PB of 1:27 vs the true 1:22 from full-log scan flipped the diagnosis). A quick one-off question need not block on setup, but any profile WRITE or fitness estimate that depends on a PB anchor must come from the full-log bootstrap.
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 · 124 lines · 4,307 tokens per session scan B a684a08b136d
oh-my-personal-best CLAUDE.md is an instructions file published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 12d ago), licensed MIT. It adds 4,307 tokens to every session, about $0.0215 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).