Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add seungwee-choi/oh-my-personal-best/plugin install 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/pb-report)<a href="https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/pb-report"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/pb-report/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/pb-report"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/pb-report.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 | $0.00017 | $0.00946 |
| Opus 5.5 | $0.00007 | $0.00378 |
| Sonnet 5.5 | $0.00003 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
pb-report 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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- The runner asks for a "report", "full report", "assessment", "리포트", "분석 리포트", "PDF"
- They want something to print, export to PDF, or send to a coach </Use_When>
<Do_Not_Use_When>
- The training log is empty — route to
/pb-setupor/pb-logfirst. - They want a quick single stat — answer via
data-logger. </Do_Not_Use_When>
Step 1 — Ensure data exists
Confirm $OMPB_HOME/training-log.jsonl exists and is non-empty (run /pb-setup first if not).
Step 2 — Diagnosis narrative (unless --no-diagnosis)
If $OMPB_HOME/diagnosis.json is missing or stale, delegate to oh-my-personal-best:race-analyst
to analyze the log (+ runner-profile.json, goal.json) and have the orchestrator write
$OMPB_HOME/diagnosis.json ({summary, limiter, observations[], generated_at}). The report's
Executive Summary, Limiter, and Key Findings sections come from this. Without it the report still
renders (those sections are empty) — prefer to generate it. The diagnosis text MUST be written in
the report's language (config.json language / --lang) — these fields are injected verbatim,
so an English diagnosis in a --lang ko report yields a mixed-language document. If an existing
diagnosis.json is in the wrong language, regenerate (or translate) it before rendering.
Step 2.5 — Fold in "와우 모먼트" insights
Run the deterministic insight pipeline and weave the most meaningful signals into the diagnosis:
python3 "$CLAUDE_PLUGIN_ROOT/scripts/insights.py" # ompb_core.detect_insights(home)
It returns score-ranked cards (cross-activity trends, self-relative PRs, hidden signals incl. a
load-spike warning). When generating/refreshing diagnosis.json in Step 2, have race-analyst
incorporate the top 2–3 cards into observations[] (e.g. "같은 심박에 두 달 전보다 12초/km 빨라짐 —
유산소 효율 향상") so they render in Key Findings without any template change. A warning card
(fatigue/load spike) belongs in the limiter/risk framing. If detect returns [] (too few runs),
skip silently — never fabricate a highlight, and never surface the detector's data limits in the report.
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.
- 2mo ago First seen · 74 lines · 17 tokens per session scan A 7c23f7ad938d
pb-report is a skill published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 946 once invoked, about $0.0001 per session on Opus 5.5. 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
brainstorm
You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
oma-hwp
Convert Hangul HWP, HWPX, or HWPML documents to Markdown with kordoc. Use for text, table, and image extraction from these formats.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
pptx
Instructions for reading, creating, and editing PowerPoint presentation files and templates, including .pptx, .potx, and older .ppt files. They cover text, tables, images, charts, layouts, and speaker notes.