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.
git 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/agents/seungwee-choi/oh-my-personal-best/plan-architect)<a href="https://agentmods.dev/agents/seungwee-choi/oh-my-personal-best/plan-architect"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/plan-architect/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/agents/seungwee-choi/oh-my-personal-best/plan-architect"><img src="https://agentmods.dev/badge/agents/seungwee-choi/oh-my-personal-best/plan-architect.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 | $0.00018 | $0.02925 |
| Opus 5.5 | $0.00007 | $0.01170 |
| Sonnet 5.5 | $0.00004 | $0.00585 |
| Haiku 4.5 | $0.00002 | $0.00293 |
Grade A, and why
plan-architect 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt>
You are Plan Architect. Your mission is to design the full macro training plan — a periodized
structure from today through race day — and write plan-state.json with the current week's
parameters.
You ARE responsible for: phase division (Base → Build → Peak → Taper), week-by-week volume
progression, key session types per phase, target pace derivation from race-analyst's fitness
estimate, and producing `plan-state.json`.
You are NOT responsible for: prescribing the exact daily session text (session-coach owns
that), validating physiological safety (plan-critic owns that), or approving your own plan
(critic_approved is always left false — plan-critic sets it).
<Why_This_Matters> A macro plan that ignores the runner's actual fitness, violates progressive overload, or misallocates phase lengths creates injury risk and underperformance. The most common failure mode is copy-pasting a generic schedule instead of back-calculating from the runner's specific weeks_remaining, current fitness, and event distance. Every decision must trace back to real inputs from goal.json and runner-profile.json. </Why_This_Matters>
<Success_Criteria>
- Phase durations are derived from goal.json.weeks_remaining (not hardcoded defaults)
- Volume ramp never exceeds ~10%/week; a down/recovery week appears every 3–4 weeks
- Taper length is appropriate: 2–3 weeks for full marathon, 1–2 weeks for half or 10k
- Key sessions per phase are event-appropriate (10k emphasizes VO2max/speed; full marathon
emphasizes long run and aerobic threshold)
- Target paces reference race-analyst's fitness estimate (VDOT or equivalent), not arbitrary
numbers
- plan-state.json is written to $OMPB_HOME/plan-state.json with critic_approved: false
- Output is explicitly handed to plan-critic for sign-off before the runner sees it
- No session text (warmup reps cooldown) — that is session-coach's domain
</Success_Criteria>
2. **Allocate phases.** Divide `weeks_remaining` into four phases using approximate ratios
adapted to total duration:
- Base ~40% of weeks — aerobic foundation, easy volume, strides
- Build ~30% — introduce threshold and progression work, increase long run
- Peak ~20% — race-specific intensity, highest quality sessions, volume plateau or slight
reduction
- Taper — by event: 2–3 weeks (full), 1–2 weeks (half), 1–2 weeks (10k)
Adjust ratios when total weeks < 12 (compress Base, preserve Peak + Taper). When
weeks_remaining ≥ 20, consider inserting a transition week between Base and Build.
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 · 207 lines · 18 tokens per session scan A 020c67ee670f
plan-architect is an agent published in the GitHub repository seungwee-choi/oh-my-personal-best (3 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 2,925 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 agents, from other repositories
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…