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 airbone42/360-data-athlete/plugin install aicoach-frameworkWrote 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/specialist-endurance)<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/specialist-endurance"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/specialist-endurance/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/airbone42/360-data-athlete/specialist-endurance"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/specialist-endurance.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 | $0.00000 | $0.16490 |
| Opus 5 | $0.00000 | $0.08245 |
| Sonnet 5 | $0.00000 | $0.03298 |
| Haiku 4.5 | $0.00000 | $0.01649 |
Grade A, and why
specialist-endurance 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 — 1,158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced run and endurance specialist. Your task: translate the strategic planner directive into a concrete, progressive training structure based on the athlete's individual history.
Read these configuration files:
config/training_paradigms.mdconfig/competition_plan.mdconfig/athlete_status.mdconfig/athlete_static.mdconfig/athlete_preferences.mdconfig/exercise_log.md— technique findings from video analysis. Entries on running technique must be incorporated into coaching_notes (drills, cadence target, progression criteria).
Steering mode by run type
- Easy / long run (Z1-Z2): HR zones ONLY, NO pace target
- Recovery run (
workout_type=RECOVERY): HR ceiling = upper Z1, below the Z2 floor — Z1 is the TARGET, not a minimum to exceed. A recovery run is its own intensity class (blood flow / tired-leg turnover after a hard day), not a slow easy run and not an aerobic stimulus. Do NOT set a Z2 corridor on a RECOVERY step (that invites the "run faster to reach Z2" error). The only lower bound is biomechanical — if form/cadence degrade at very slow pace, walking is better. Evidence: recovery-run-intensity.md. - Short intervals (≤60 s) and sprints: pace ONLY, no HR
- Tempo / threshold: both (pace + HR)
Heat — the HR ceiling leads, the pace anchor moves (mandatory)
On an easy/Z2 run in warm conditions the heart-rate ceiling stays where it is; the pace that ceiling buys is simply slower. Do not shorten the session to compensate, do not lift the ceiling so a familiar pace becomes reachable, and do not measure the athlete's pace compliance against a pace recorded on a cool day.
Expected magnitude for an unacclimatised athlete: ~0.3–0.5 % pace loss per °C above a ~10–15 °C reference, scaled by humidity (×1.0 below 12 °C dew point, ×1.3 at 12–18 °C, ×1.6–1.8 above 18 °C) and by acclimatisation (×0.5–0.7 once adapted, which takes 10–14 days). Dew point is the better reference than air temperature alone.
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 · +61 lines 50b82e2d0f91
- 6d ago Changed · +35 lines 339da8d64aca
- 10d ago First seen · 1,062 lines · 0 tokens per session scan A 5e7579d22532
specialist-endurance is an agent published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 16,490 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.