token-coach

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: token-coach
description: Plan a token-efficient Claude Code or Codex setup, or get a quick health check. Coaching, not the full audit (use token-optimizer for that).
---

# Token Coach: Plan Token-Efficient Before You Build

> **Never recommend cutting our own tools (issue #111).** When you surface optimization or setup-overhead recommendations, NEVER suggest removing, archiving, trimming, disabling, or consolidating Token Optimizer's own skills — `token-optimizer`, `token-coach`, `token-dashboard`, `fleet-auditor`. They are the measurement layer; a tool that tells the user to delete itself to "save ~200 tokens" is self-defeating and embarrassing. Exclude them from every unused-skill / archive / consolidation suggestion, no matter how rarely they were invoked (an audit tool you don't explicitly call is not an "unused" skill).

Interactive coaching for Claude Code or Codex architecture decisions. Analyzes your setup, identifies patterns (good and bad), and gives personalized advice with real numbers.

**Use when**: Building something new, existing setup feels slow, designing multi-agent systems, or want a quick health check.

---

## Phase 0: Initialize

1. **Resolve runtime and measure.py path** (same as token-optimizer):
```bash
RUNTIME="${TOKEN_OPTIMIZER_RUNTIME:-}"
if [ -z "$RUNTIME" ]; then
  if [ -n "$CLAUDE_PLUGIN_ROOT" ] || [ -n "$CLAUDE_PLUGIN_DATA" ]; then
    RUNTIME="claude"
  elif [ -n "$OPENCODE" ] || [ -n "$OPENCODE_BIN" ] || [ -n "$OPENCODE_CONFIG_DIR" ] || [ -n "$OPENCODE_CONFIG" ]; then
    RUNTIME="opencode"
  elif [ -n "$CODEX_HOME" ]; then
    RUNTIME="codex"
  elif [ -n "$CLAUDECODE" ] || [ -n "$CLAUDE_CODE_ENTRYPOINT" ] || [ -n "$CLAUDE_CODE_SESSION_ID" ]; then
    RUNTIME="claude"
  elif [ -d "$HOME/.config/opencode" ] && [ ! -d "$HOME/.codex" ]; then
    RUNTIME="opencode"
  elif [ -d "$HOME/.codex" ]; then
    RUNTIME="codex"
  else
    RUNTIME="claude"
  fi
fi

# Resolve measure.py to the NEWEST installed copy across channels so a stale
# plugin-cache copy never shadows a fresh install (issue #57). find -L follows the
# install.sh symlink under ~/.claude/skills; cd -P resolves it before reading each
# copy's plugin.json for its version. find (not bare globs) never errors under zsh.
MEASURE_PY=""; _best_ver=""
while IFS= read -r _cand; do
  [ -f "$_cand" ] || continue
  _root="$(cd -P -- "$(dirname -- "$_cand")/../../.." 2>/dev/null && pwd)"
  _ver="$(sed -n 's/.*"version"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p' "$_root/.claude-plugin/plugin.json" 2>/dev/null | head -1)"
  [ -n "$_ver" ] || _ver="0.0.0"
  if [ -z "$_best_ver" ] || [ "$(printf '%s\n%s\n' "$_ver" "$_best_ver" | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -n1)" = "$_ver" ]; then
    _best_ver="$_ver"; MEASURE_PY="$_cand"
  fi
done <<EOF
$(find -L "$HOME/.claude/skills" "$HOME/.claude/plugins/cache" "$HOME/.claude/token-optimizer" "$HOME/.codex/skills" "$HOME/.codex/plugins/cache" "$HOME/.config/opencode/plugins/cache" "$HOME/.config/opencode/plugins" -type f -name measure.py -path '*token-optimizer*/scripts/measure.py' 2>/dev/null)
EOF
if [ -z "$MEASURE_PY" ] || [ ! -f "$MEASURE_PY" ]; then echo "[Error] measure.py not found. Is Token Optimizer installed?"; exit 1; fi
export TOKEN_OPTIMIZER_RUNTIME="$RUNTIME"
```

2. **Collect coaching data**:
```bash
python3 "$MEASURE_PY" coach --json
```
Parse the JSON output. This gives you: snapshot (current measurements), detected patterns, coaching questions, focus suggestions, and **history** (trend data from past sessions).

The `history` key contains (when trends.db has enough data):
- `quality_recent_avg` / `quality_prior_avg` - 7-day vs older quality scores
- `duration_recent_avg` / `duration_prior_avg` - session length trends (minutes)
- `cache_hit_recent_avg` / `cache_hit_prior_avg` - prompt cache hit rate trends
- `grade_d_pct_recent` / `grade_distribution` - recent grade breakdown
- `total_cost_usd` / `cost_per_session_usd` / `sessions_in_period` - spend summary
- `quality_sho