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/weekly-adapt)<a href="https://agentmods.dev/skills/seungwee-choi/oh-my-personal-best/weekly-adapt"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/weekly-adapt/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/weekly-adapt"><img src="https://agentmods.dev/badge/skills/seungwee-choi/oh-my-personal-best/weekly-adapt.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 | $0.02290 |
| Opus 5.5 | $0.00006 | $0.00916 |
| Sonnet 5.5 | $0.00003 | $0.00458 |
| Haiku 4.5 | $0.00001 | $0.00229 |
Grade A, and why
weekly-adapt 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- The runner checks in at the end of or during a training week ("이번 주 계획 조정해줘", "weekly check-in", "adjust this week", "how did I do?")
- Keyword triggers detected: "weekly", "이번 주", "adjust", "week check-in", "this week"
- A new week is starting and the runner wants next week calibrated to actual last-week performance
- plan-state.json exists and
critic_approved: true(an active plan is in progress) - After recovering from illness or a missed-session cluster and the plan needs resetting </Use_When>
Step 1 — Collect and Aggregate Actuals (data-logger + deterministic adherence)
If the runner provided check-in notes in $ARGUMENTS, pass them to oh-my-personal-best:data-logger
first (natural-language path) so any new sessions are normalized into training-log.jsonl before
aggregation.
Then compute the week's adherence DETERMINISTICALLY (don't hand-tally):
python3 "$CLAUDE_PLUGIN_ROOT/scripts/review.py" aggregate --offset 0 # or ompb_core.week_review_aggregate(home, 0)
This overlays plan-week.json on the actual runs and returns the evidence base every downstream
agent uses: per-day adherence verdicts (done / skipped / upcoming / rest_kept / unplanned /
skipped_injury), adherence % (completed/planned), planned↔actual volume vs target_km,
key-session execution (key_done/key_planned), and goal + injury context. A session missed
during an active injury is skipped_injury (recovery), never a penalised lapse — read it that way.
data-logger's intensity-distribution summary complements this. Do not proceed until the aggregate
is in hand.
Retrospective review vs. adaptation — keep them separate. The weekly review (Step 6's "this
week" narrative) is a look back; the adaptation (Steps 4–5) sets next week. A review NEVER
prescribes specific sessions ("go run X today") — that's the plan's job. And do not auto-generate a
"week complete" review for an INCOMPLETE week: use week_review_status(home, 0).ready — only True
(the last planned training day is today-or-past and done, nothing past-due still pending, ≥1 run
logged) means the week is reviewable as finished. Mid-week, adapt forward without a finished-week verdict.
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 · 178 lines · 14 tokens per session scan A 75f40c3b7eed
weekly-adapt is a skill published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,290 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
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.
stack-baseline
The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
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…