save_strategy
shallowrun.stas/stas · Verify this server
Save the athlete preparation map only after explicit user confirmation. The map is the reusable result of long-horizon planning, not a calendar, weekly plan, workout prescription, or full coaching analysis. Target length is about 1800-4000 characters; hard maximum is 5000 characters. Required sections: Goal direction, Current phase, Preparation map, Durable boundaries, Review triggers / unknowns. Build from current goals, rules, profile, lastMetrics, wellness, training history, evidence, reports, and calendar first; treat previous strategy as historical context and contamination risk. Use at least 8 weeks of weekly/load history when available and 12-26 weeks for season direction, combined with exact bounded-list windows and selected detailed workout passports. Treat every dated goal as a real input and infer priority only when explicit. Store the agreed goal relationships, current phase purpose, a broad 3-6 phase route, what each phase develops/preserves/defers, transition conditions, durable boundaries, and causal review triggers. A phase may name its target capacity. Every Durable boundaries line must preserve a route-specific decision and must not repeat universal coaching, measurement, device, load-cost, or athlete rules. Local pain, sleep, recovery, illness, or execution signals change the near-term plan first and become map review triggers only when persistence would change phase feasibility, timing, sequence, or the goal route. Treat phase dates as approximate anchors and Transition when as review evidence, not hard gates; if unmet, consider adaptation, delayed or compressed transition, and remaining runway. Do not store session frequency, easy/hard balance, weekly load targets, number of key workouts, default weekly stimuli, exact progression, workout formats/protocols, fixed taper depth, ready 2-4 week sequences, current Fitness/Fatigue/Form/TL, loaded windows, or live calendar state. Old detailed strategies remain historical context: do not proactively ask the athlete to convert one merely because an internal audit calls it legacy. Create or update the map only when the athlete asks for strategy/season work or explicitly agrees to a long-term route change. Before calling this tool, show the exact full markdown and ask for explicit confirmation. Never show one version and save another.
1 trials · measured 8 days ago
save_strategy scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against run.stas/stas, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- gated
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-08-25 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/47adf95e-06d1-4b97-bb5d-dd7105936e40)