القائمة
Audit token waste across agent systems (Claude Code, Codex, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Find the ghost tokens. Audit Claude Code or Codex setup, see where context goes, fix it. Use when context feels tight.
Find the ghost tokens. Audit Claude Code or Codex setup, see where context goes, fix it. Use when context feels tight.
Context window coach analyzing setup overhead, historical usage trends, and session habits. Use when building something new and wanting token efficiency from the start, existing sessions feel sluggish or context fills too fast, designing multi-agent systems, or wanting a quick health check with real numbers. Do NOT use for running the full audit and applying fixes (use /token-optimizer instead).
Open the Token Optimizer dashboard. Collects latest session data, regenerates the dashboard, and opens it in your browser.
Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities
| name | fleet-auditor |
| description | Audit token waste across agent systems (Claude Code, Codex, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings. |
Detects installed agent systems, collects token usage data, identifies waste patterns, and recommends fixes with dollar savings estimates. Everyone tracks. Nobody coaches. Until now.
Use when: Running multiple agent systems, spending $2-5/day on agents, suspecting idle heartbeats are burning tokens, or want a cross-system cost audit.
RUNTIME="${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 [ -d "$HOME/.config/opencode" ] && [ ! -d "$HOME/.codex" ]; then
RUNTIME="opencode"
elif [ -d "$HOME/.codex" ]; then
RUNTIME="codex"
else
RUNTIME="claude"
fi
fi
# Resolve fleet.py to the NEWEST installed copy across channels so a stale
# plugin-cache copy never shadows a fresh install (issue #57). find -L follows the
# install.sh symlink under ~/.claude/skills; cd -P resolves it before reading each
# copy's plugin.json for its version. find (not bare globs) never errors under zsh.
FLEET_PY=""; _best_ver=""
while IFS= read -r _cand; do
[ -f "$_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"; FLEET_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 fleet.py -path '*fleet-auditor*/scripts/fleet.py' 2>/dev/null)
EOF
if [ -z "$FLEET_PY" ]; then echo "[Error] fleet.py not found. Is Fleet Auditor installed?"; exit 1; fi
echo "Using: $FLEET_PY"
export TOKEN_OPTIMIZER_RUNTIME="$RUNTIME"
Use $FLEET_PY for all subsequent fleet.py calls.
python3 "$FLEET_PY" detect --json
Parse the JSON output. Report what was found.
If nothing detected, explain: "No agent systems found. Fleet Auditor supports: Claude Code, Codex, OpenClaw, NanoClaw, Hermes, OpenCode, IronClaw."
Collect token usage data from detected systems:
python3 "$FLEET_PY" scan --days 30
Report how many runs were collected per system. If this is the first scan, it may take a moment to parse all session files.
Run waste pattern detection:
python3 "$FLEET_PY" audit --json
Parse the JSON output. Present findings ordered by severity and monthly savings.
If no waste found: "Your fleet looks clean. No significant waste patterns detected."
For Codex findings, be careful with dollars: if a model's pricing is not in the local pricing table, present token waste confidently and say dollar impact depends on current model pricing instead of inventing a cost.
OpenClaw Security + Cost Check (March 2026):
openclaw config set security.rateLimit.enabled true[Fleet Auditor Results]
SYSTEMS DETECTED
- Claude Code: X runs ($Y.YY)
- Codex: X runs ($Y.YY)
- OpenClaw: X runs ($Y.YY)
WASTE PATTERNS FOUND
1. [SEVERITY] Description
Est. savings: $X.XX/month
Fix: recommendation
2. [SEVERITY] Description
...
TOTAL POTENTIAL SAVINGS: $X.XX/month
Ready to act? I can:
1. Show detailed fix snippets for each finding
2. Generate the fleet dashboard for visual analysis
3. Run /token-optimizer for deeper Claude Code optimization
If user wants visual analysis:
python3 "$FLEET_PY" dashboard
This generates ~/.claude/_backups/token-optimizer/fleet-dashboard.html in Claude Code, or ~/.codex/_backups/token-optimizer/fleet-dashboard.html when TOKEN_OPTIMIZER_RUNTIME=codex.
For Claude Code specifically, offer /token-optimizer for full audit (CLAUDE.md, skills, MCP, hooks, etc.).
For Codex specifically, offer token-optimizer for full audit (AGENTS.md, Codex memories, plugin skills, MCP, balanced hooks, compact prompt, status line).
For other systems, show the fix snippets from the audit and guide the user through implementing them.
| Phase | Read |
|---|---|
| Adapter development | references/fleet-systems.md |
| Detector development | references/waste-patterns.md |
--days