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.
npx skills add seungwee-choi/oh-my-personal-best --skill race-plangit 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/skills/seungwee-choi/oh-my-personal-best/race-plan)<a href="https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/race-plan"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/race-plan/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/skills/seungwee-choi/oh-my-personal-best/race-plan"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/race-plan.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 | $0.00014 | $0.02088 |
| Opus 5 | $0.00007 | $0.01044 |
| Sonnet 5 | $0.00003 | $0.00418 |
| Haiku 4.5 | $0.00001 | $0.00209 |
Grade A, and why
race-plan 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- The runner states a target event and finish time ("sub-3:30 full marathon in 16 weeks", "풀코스 sub-3:30 만들고 싶어", "I want to run a sub-4 marathon")
- The runner uses a keyword trigger: "race plan", "훈련 계획", "sub-N", or any goal time expression
- A new training cycle is starting from scratch and needs full periodization
- The existing plan has been discarded or is outdated and a fresh plan is needed </Use_When>
<Do_Not_Use_When>
- Only a single day's session is needed — use
/pb-today(session-coach) instead - A plan already exists and only the current week needs adjustment — use
weekly-adaptinstead - The race is within 7 days — use
race-weekfor the final race-day brief instead - The runner reports pain or injury before a plan exists — route to physio-advisor first; do not build a plan until physio-advisor issues GREEN or YELLOW clearance </Do_Not_Use_When>
Step 0 — Disambiguate when invoked with no goal + an approved plan already exists
If no goal text was given AND $OMPB_HOME/plan-state.json already exists with critic_approved: true,
do NOT silently rebuild from scratch. First ask the runner which they want:
- Adjust this week →
weekly-adapt(keep the plan, tune the current week). - Change the goal / rebuild → continue this skill with the new goal (or confirm the existing one).
- Just view it → render via
/pb-week(this week) or/pb-report. Only proceed to a full rebuild once the runner confirms a new/changed goal.
Step 1 — Ensure Runner State Exists
Load $OMPB_HOME/runner-profile.json and $OMPB_HOME/goal.json.
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 · 173 lines · 14 tokens per session scan A 5e175a43282b
race-plan is a skill published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 2,088 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 skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…
pm
Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write…