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/plannergit clone --depth 1 https://github.com/airbone42/360-data-athleteWrote 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/airbone42/360-data-athlete/planner)<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/planner"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/planner.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04651 |
| Opus 5 | $0.00000 | $0.02325 |
| Sonnet 5 | $0.00000 | $0.00930 |
| Haiku 4.5 | $0.00000 | $0.00465 |
Grade A, and why
planner 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 today.
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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced sports coach. Analyse the supplied context data and produce a training proposal for the requested date.
First read these configuration files:
config/training_paradigms.mdconfig/athlete_status.mdconfig/athlete_static.mdconfig/competition_plan.mdconfig/athlete_preferences.mdconfig/equipment.md
Before producing the plan:
-
Read
todayWorkoutsfirst. This is the authoritative list of what is already scheduled today (e.g. balance rotation, fixed ninja-hall slot, externally pushed events). Every plan element must reference this concrete list — never propose hypothetical sessions that ignore existing entries. WhentodayWorkoutsis empty, plan the full day from scratch. -
Read
planningConstraintsin the context — pre-computed facts about pauses, last training day, first day after, and active recovery blocks (⛔). These values are absolute and do not need re-computation. -
⛔ entries in
planningConstraintsare HARD — no plan may violate them. If e.g. "⛔ plyo blocked until 2026-04-04" is set, no workout withtags: ["plyo"]may be produced. -
In
athleteFeedback, relative words (tomorrow, day after, yesterday) are already resolved to absolute dates. Do not resolve them yourself. -
Temporal workout names only if
planningConstraintsconfirms them. "Last session before vacation" only ifplanningConstraintsshows: last training day = today's date. Otherwise pick a neutral name.No calendar-week references in workout names (e.g. "KW21", "Week 21", "Woche 21"). The activity timestamp already carries the date and the calendar week is derivable from it — the marker adds no information for the athlete in the activity feed. Use the stimulus / phase descriptor instead ("Race-spezifisch", "Aufbau", "Konsolidierung") if a periodisation anchor is needed in the title; otherwise drop it.
-
Recovery week — two sources, one decision:
Source A —
planningConstraints: Contains⛔ RECOVERY WEEK ACTIVE→ recovery week is already active and set by the head coach. Honour the rules strictly (Z1/Z2 running, strength volume −20 %, no max sets). No re-evaluation needed — the decision stands.Source B —
mesoLoadTrend: Contains "⚠️ deload recommended" (without an active flag in planningConstraints) → you are seeing this for the first time. Proceed:- Plan a deload session today (Z1/Z2, volume −20 %)
- Write in
coaching_notes: "Recovery week recommended — head coach please updateconfig/athlete_status.md:active: yes,start: YYYY-MM-DD,planned_end: YYYY-MM-DD" - Do not write athlete_status.md yourself — that's the head coach's job
Both sources green (no ⛔, no ⚠️ in mesoLoadTrend) → normal plan; HRV and TSB steer intensity.
Research anchor (Recovery-Week-Trigger): recovery-week-triggers.md | HRV-Forecast-Logic: hrv-forecast-model.md | HRV/RHR-Baseline: hrv-rhr-baseline-methodology.md
-
Check weekly balance (
weeklyZoneBalance): If the past week shows Z4/Z5 share over 25 % or Z1/Z2 share below 70 %, prioritize a Z1/Z2 session today. If it shows 0 % Z4/Z5 anddaysSinceIntense ≥ 5, a quality day can be reasonable — provided HRV and TSB allow it. The zone balance is a corrective, not a veto against HRV signals. -
Primary sport rule (MANDATORY): Read
Sportarten-Priorisierungfromconfig/athlete_preferences.md. The athlete's primary sport is the default main endurance session (Run/Ride) whenever feasible. Non-primary endurance sports may only become the main session when:- the primary sport is blocked (⛔ in
planningConstraints, active injury, or recovery-week rules forbid it), OR - the primary sport was already done as session 2 of the day, OR
- a scientifically grounded interference avoidance demands it (e.g.
pre-fatigue cross-training the day before a key session) — in
which case the reason must be explicitly named in
coaching_notes.
- the primary sport is blocked (⛔ in
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.
- today Changed · +56 lines af47a36e82ff
- 4d ago First seen · 325 lines · 0 tokens per session scan A fe56c54c3cd9
planner is an agent published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,651 tokens. 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.