A race-week planning brief assembled from the runner's goal, profile, training history, current training phase, and race details.

Use it within seven days of a race for taper and race-day guidance, including details such as the course, weather, start time, and aid stations.

It brings the final week's decisions into one pre-race view and checks for recent pain or unresolved safety concerns.

race-week — Skill for Claude Code by seungwee-choi

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.

Any agent

npx skills add seungwee-choi/oh-my-personal-best --skill race-week

Clone the repo

git clone --depth 1 https://github.com/seungwee-choi/oh-my-personal-best

Made for: Claude Code.

Or install oh-my-personal-best, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 8 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/race-week/github.svg)](https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/race-week)

Your own site

<a href="https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/race-week"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/race-week/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/race-week"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/race-week.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,477 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.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.01477
Opus 5	$0.00006	$0.00739
Sonnet 5	$0.00002	$0.00295
Haiku 4.5	$0.00001	$0.00148

Measured 12d ago against content hash 91bb1a6e6892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

race-week 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.

skills/race-week/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Use_When>

The race is within 7 days ("다음 주가 대회야", "race is next week", "race week", "대회 D-7", "taper", "race on Sunday")
Keyword triggers detected: "race week", "대회 D-7", "taper", "race day", "race is [day]"
The runner explicitly requests a race-day brief or pre-race guidance
goal.json race_date is within 7 days of today </Use_When>

Step 1 — Load Context

Before firing the parallel consult, load:

$OMPB_HOME/goal.json — event, target_time, race_date, weeks_remaining
$OMPB_HOME/runner-profile.json — current_pb, weight_kg, experience, injury_history
$OMPB_HOME/plan-state.json — current phase (should be taper), plan_week, this_week_target_km, critic_approved
Recent $OMPB_HOME/training-log.jsonl — last 21 days to assess taper compliance and detect any late-appearing pain signals

Pass $ARGUMENTS (if provided) as additional race context — course profile, expected weather, start time, aid-station spacing — to all three parallel agents.

Safety gate: if the training log shows any unresolved RED verdict from physio-advisor, or any pain signal in the last 7 days, route to physio-advisor synchronously before firing the parallel consult. Do not produce a race-day brief while a RED verdict is active.

Step 2 — Parallel Consult (pace-strategist + fuel-advisor + physio-advisor)

Fire all three agents simultaneously. Do not wait for one before starting the others.

pace-strategist (`oh-my-personal-best:pace-strategist`)

Produces the racing strategy brief:

Goal assessment: target time vs. fitness-predicted time, feasibility rating
Target goal pace (MM:SS/km) and plan-B pace
Per-km or per-5-km split table with cumulative times
Course and weather adjustments (if race details provided in $ARGUMENTS)
Segment effort cues per race third (conversational / controlled / working / race mode)
Pacing rules (3–5 numbered, e.g., "The first km will feel too easy — that is the plan")
Plan-B: trigger condition (off goal pace at midpoint check), fallback time and pace
Fueling checkpoint km markers (timing only — fuel-advisor provides amounts)

Read the full file on GitHub · 127 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.

12d ago First seen · 127 lines · 12 tokens per session scan A 91bb1a6e6892

Subscribe to this mod's changes

race-week is a skill published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 12d ago), licensed MIT. It adds 12 tokens to every session and 1,477 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.

Claude Code Multi-Agent Planning Scientific ai-agents claude-code-plugin marathon running

relax-dev-debug

Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.

redai-infra/Relax · 60 tokens

great_cto

Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.

avelikiy/great_cto · 32 tokens

local-paper-navigator

Find and read papers from the local papers library (repo papers/, mounted at /papers/). Three native tools form a reading funnel: papersearch (one line per paper), paperread (card + section outline), papersection (one verbatim section — the only full-text access). Use when: find papers in the local library, read a…

CamusGIT/EvoQuant · 119 tokens

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).

avelikiy/great_cto · 59 tokens

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.