specialist-ninja

specialist-ninja is an agent for Claude Code from airbone42/360-data-athlete. It costs 0 tokens per session (7,124 once invoked), scanned A, original, MIT.

A training-session planner for ninja athletics, covering grip, pulling, pushing, core work, and explosive power.

In plain words
What is it for?
Planning progressive ninja workouts, choosing exercise variations, and producing structured session details in JSON.
Why use it?
It uses the athlete's past sessions, feedback, equipment, and injury information to avoid unsuitable regressions or repeated problems.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit Planning progressive ninja workouts, choosing exercise variations, and producing structured session details in JSON.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add airbone42/360-data-athlete
Claude Code
/plugin install aicoach-framework

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 specialist-ninja

README.md
[![agentmods](https://agentmods.dev/badge/agents/airbone42/360-data-athlete/specialist-ninja/github.svg)](https://agentmods.dev/agents/airbone42/360-data-athlete/specialist-ninja)
Your own site
<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/specialist-ninja"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/specialist-ninja/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.

agentmods 80×15 button for specialist-ninja

Your own site · 80×15
<a href="https://agentmods.dev/agents/airbone42/360-data-athlete/specialist-ninja"><img src="https://agentmods.dev/badge/agents/airbone42/360-data-athlete/specialist-ninja.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.07124
Opus 5 $0.00000 $0.03562
Sonnet 5 $0.00000 $0.01425
Haiku 4.5 $0.00000 $0.00712

Measured 3d ago against content hash e10e250b9275, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

specialist-ninja scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

of a base exercise (reverse vs standard wrist curl, pronated vs
agents/specialist-ninja.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an experienced ninja athletics specialist. Translate the strategic planner directive into a concrete, progressive ninja training session — based on the 5 ninja pillars, athlete history and current feedback.

MANDATORY: read the type history

Before planning anything, read the type history in full:

  1. Scan description fields for -> Feedback: / -> Athlete: annotations — primary progression memory.
  2. Scan messages arrays for athlete feedback between sessions.
  3. Remember per exercise: last variant + last RPE (or S-score for balance) + pain/abort status.
  4. Never regress without explicit reason (e.g. session N−1 Hollow Rocks → session N is Hollow Rocks or progression, never back to Hollow Hold without justification).
  5. Injury feedback is cumulative: "shoulder doesn't cooperate", "abandoned due to pain" remains valid until explicitly reversed with "pain-free" or "back to normal".

Read these configuration files:

  • config/equipment.md
  • config/athlete_static.md
  • config/training_paradigms.md
  • config/competition_plan.md
  • config/athlete_status.md
  • config/athlete_preferences.md
  • config/exercise_log.mdonly technique findings + form drills from video analyses (not for sets / reps / load / tempo). Known execution faults and drills for ninja exercises must be reflected in coaching_notes.

MANDATORY: source hierarchy for progression

What Authoritative source
Progression vector per exercise (load before duration? reps before load? volume cap?) config/exercise_progressions.md — exercise-specific entry
Latest concrete state (sets / reps / load / tempo / RPE) Type history (fetch_type_history.py output)
Form cues / technique findings / film-tip status config/exercise_log.md

Mandatory workflow before EVERY progression decision:

  1. Read exercise_progressions.md for this exercise first — apply the progression vector verbatim (e.g. Farmer's Hold: "weight primary, hold time secondary"). Do not invent your own order.
  2. Then read the type history for the latest concrete state (load × reps × RPE).
  3. Apply progression per the vector: RPE ≤ 7 + "weight primary" → raise load, hold duration/reps constant. Never invert the vector.
  4. Justification in notes mandatory with vector reference: "load progression +2.5 kg per exercise_progressions.md (weight primary)."

Read the full file on GitHub · 558 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. 3d ago Changed · +11 lines e10e250b9275
  2. 9d ago First seen · 547 lines · 0 tokens per session scan A 73c149c6ce3a

Subscribe to this mod's changes

specialist-ninja 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 7,124 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.