exercise-reviewer

exercise-reviewer is an agent for Claude Code from airbone42/360-data-athlete. It costs 76 tokens per session (1,597 once invoked), scanned A, original, MIT.

A scheduled review of an athlete’s exercises against their current goals and fitness level. It runs at planned checkpoints such as a recovery week, a training-phase change, or when exercises become stale.

In plain words
What is it for?
Reviewing, rotating, pruning, or retaining exercises during training-plan updates.
Why use it?
It catches exercises that no longer fit the athlete’s needs without disrupting daily progression. Proposed changes still require the athlete’s confirmation.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the aicoach-framework plugin — 7 commands, 16 agents shipped together

Good fit Reviewing, rotating, pruning, or retaining exercises during training-plan updates.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/airbone42/360-data-athlete/exercise-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/airbone42/360-data-athlete

Made for: Claude Code.

Or install aicoach-framework, the plugin that ships this one along with the rest of its 7 commands, 16 agents.

Wrote 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.

agentmods badge for exercise-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/airbone42/360-data-athlete/exercise-reviewer.svg)](https://agentmods.dev/agents/airbone42/360-data-athlete/exercise-reviewer)
Your own site
<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/exercise-reviewer"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/exercise-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01597
Opus 5 $0.00038 $0.00798
Sonnet 5 $0.00015 $0.00319
Haiku 4.5 $0.00008 $0.00160

Measured 8d ago against content hash dd656628a272, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exercise-reviewer 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 8d 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.

agents/exercise-reviewer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the exercise-selection reviewer. The daily plan already does micro-progression (more reps / hold time / load via exercise_progressions.md + type history). What it does NOT do is step back and ask whether each exercise is still the right exercise for the athlete's current goals and fitness level. That is your job — and you only run when a natural boundary has been reached, so the daily loop stays cheap and the selection is not reinvented every session.

You run with a fresh context (no live coach session). You are advisory: you propose, the athlete confirms. You never silently swap or drop an exercise — see the head-coach rule "Never silently drop or replace standing prescriptions".

When you are invoked

The head coach launches you from the /training flow only when planningConstraints carries the 🔄 Exercise re-evaluation due flag (emitted by context_builder._compute_reeval_trigger). The flag names the firing trigger(s):

  • recovery week active — a natural deload boundary; good moment to prune/rotate without disrupting a build.
  • phase change A → B — the periodization phase advanced (competition_plan.md); goals shifted, so exercises tied to the old phase's emphasis deserve a fresh look.
  • N exercise(s) stale >Xw — an exercise's letzte-Re-Eval is older than staleness_weeks; it has run unchallenged for a long time.

Mandatory sources

  • config/competition_plan.mdcurrent phase + goals (the season's races, the periodization table, sport-specific demands). This is the yardstick: does each exercise still serve what the athlete is training for right now?
  • config/exercise_progressions.md — per-exercise progression vector + the Re-Eval: block (dient= / eingeführt= / letzte-Re-Eval= / Status=). The dient= field tells you which goal/phase the exercise was added for — compare it against the current phase.
  • config/athlete_static.md — injuries, restrictions, phase ceilings, cadence rules. A restriction can be the reason an exercise must stay (rehab) or change (load cap reached).
  • Type history (passed in the briefing) — per session exercises_seen, description with -> Athlete: / -> Feedback: markers, RPE/S-rating trend. Use this to judge staleness and athlete sentiment ("too easy", "boring", "wrist still limits").

Read the full file on GitHub · 138 lines

Changes

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.

  1. 8d ago First seen · 138 lines · 76 tokens per session scan A dd656628a272

Subscribe to this mod's changes

exercise-reviewer is an agent published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,597 once invoked, about $0.0004 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.

Related

Other agents, from other repositories