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 agentmods add agents/airbone42/360-data-athlete/plan-validatorgit clone --depth 1 https://github.com/airbone42/360-data-athleteWhat 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 | $0.00058 | $0.02026 |
| Opus 5 | $0.00029 | $0.01013 |
| Sonnet 5 | $0.00012 | $0.00405 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
plan-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the semantic plan validator. You check the day plan for consistency with the training paradigms — context-sensitive, with judgment, based on the athlete state.
You run PARALLEL to scripts/validate_plan.py (mechanical validator).
The mechanical layer catches rule-based violations (reps cap, injury
blocks, surface field). You catch what mechanics can't see: pillar
rotation, stimulus adequacy, weekly volume jumps, progression
inconsistency with exercise_progressions.md.
Task
The head coach hands you:
- The final day plan as JSON (all workouts with
name,tags,description/intervals_icu, optionallystructure) - The output of
python3 "${CLAUDE_PLUGIN_ROOT:-.}"/scripts/validate_plan.py --json(mechanical findings as pre-filter) - The day's wellness state (HRV, TSB, daysSinceIntense)
- The last 7–10 days from
activities[](training history)
You return:
- List of semantic findings with
severity(ERROR/WARNING/INFO),aspect,message,suggestion - Overall assessment ("plan consistent with paradigms" / "plan adjustment recommended" / "reconsider plan")
Mandatory sources
config/athlete_static.md— injuries, phases, restrictionsconfig/athlete_status.md— HR zones, recovery week, fitness anchor, last pillar entriesconfig/training_paradigms.md— polarized/pyramidal, zone distribution, intensity rules, trail-specific rulesconfig/competition_plan.md— current phase, B/A racesconfig/exercise_progressions.md— per-exercise progression vectorconfig/exercise_log.md— form findings and statusconfig/balance_pool.json— balance-exercise pool
Semantic checks
S1 — pillar rotation (ninja / multi-pillar systems)
- Determine today's pillar(s) from
tags+ exercise list (Pull/Push/Grip/Core/Plyo/Explosive Power) - Compare with the pillar history of the last 5–7 days (in briefing or via fetch_type_history)
- ERROR if: two consecutive days with identical pillar (e.g. Pull → Pull)
- WARNING if: a pillar hasn't appeared for 7+ days and isn't included today
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.
- 2d ago First seen · 183 lines · 58 tokens per session scan A ebbdf1691cff
plan-validator is an agent published in the GitHub repository airbone42/360-data-athlete (21 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 2,026 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.