--- name: Fleet Auditor slug: fleet-auditor category: AI Engineering description: Fleet Auditor detects installed agent systems, collects token usage data, identifies waste patterns, and recommends fixes with dollar savings estimates. Use it when running multiple agent systems, spending $2-5/day on agents, or suspecting idle heartbeats are burning tokens. github: "https://github.com/alexgreensh/token-optimizer/tree/main/skills/fleet-auditor" language: Python stars: 1909 forks: 154 install: "npx degit https://github.com/alexgreensh/token-optimizer/tree/main/skills/fleet-auditor ~/.claude/skills/fleet-auditor" installs_to: ~/.claude/skills/fleet-auditor source_path: skills/fleet-auditor/SKILL.md collection_size: 6 category_size: 2451 collection_url: "https://dirskills.com/collections/alexgreensh/token-optimizer" added: 2026-08-18T06:59:09.889Z last_synced: 2026-08-18T06:59:09.889Z canonical_url: "https://dirskills.com/skills/fleet-auditor" --- # Fleet Auditor Fleet Auditor detects installed agent systems, collects token usage data, identifies waste patterns, and recommends fixes with dollar savings estimates. Use it when running multiple agent systems, spending $2-5/day on agents, or suspecting idle heartbeats are burning tokens. **Install:** ```bash npx degit https://github.com/alexgreensh/token-optimizer/tree/main/skills/fleet-auditor ~/.claude/skills/fleet-auditor ``` ## README # Fleet Auditor: Cross-Platform Agent Token Waste Auditor > **Never recommend cutting our own tools (issue #111).** When recommending fixes, 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; telling the user to delete them to "save ~200 tokens" is self-defeating. Exclude them from every unused-skill / archive / consolidation suggestion. 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 $2-5/day on agents, suspecting idle heartbeats are burning tokens, or want a cross-system cost audit. --- ## Phase 0: Initialize 1. **Resolve runtime and fleet.py path** (works for both skill and plugin installs): ```bash RUNTIME="${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 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="$_cand" fi done </dev/null) EOF if [ -z "$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 `$FLEET_PY` for all subsequent fleet.py calls. 2. **Detect systems**: ```bash python3 "$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." --- ## Phase 1: Scan Collect token usage data from detected systems: ```bash python3 "$FLEET_PY" scan --days 30 ``` Report how many runs were collected per system. If this is the first scan, it may take a moment to parse all session files. --- ## Phase 2: Audit Run waste pattern detection: ```bash python3 "$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): - If OpenClaw is detected and version < 2026.3.12: flag as HIGH severity. 31 CVEs including ClawJacked (full agent takeover). Compromised instances run rogue agents that burn tokens undetected. Recommend immediate upgrade. - Check for ClawHub skills matching ClawHavoc campaign patterns (1,184+ malicious skills). These skills exfiltrate data via extra API calls, inflating token spend. - Flag if gateway rate limiting is disabled (CVE-2026-25253). Without it, brute-force attacks can spawn unlimited agent sessions. Recommend: `openclaw config set security.rateLimit.enabled true` --- ## Phase 3: Present Findings ``` [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: $X.XX/month Ready to act? I can: 1. Show detailed fix snippets for each finding 2. Generate the fleet dashboard for visual analysis 3. Run /token-optimizer for deeper Claude Code optimization ``` --- ## Phase 4: Dashboard (optional) If user wants visual analysis: ```bash python3 "$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`. --- ## Phase 5: Deep Dive (optional) 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. --- ## Reference Files | Phase | Read | |-------|------| | Adapter development | `references/fleet-systems.md` | | Detector development | `references/waste-patterns.md` | --- ## Error Handling - **No systems detected**: Report cleanly, list supported systems - **Empty scan results**: System detected but no session data in window. Suggest increasing `--days` - **Permission errors**: Report which files couldn't be read, continue with available data - **Corrupted data**: Skip bad files, report count of skipped files - **fleet.py not found**: Check both skill and plugin install paths --- ## Core Rules - Quantify everything in dollars AND tokens - Never read or expose message content (privacy-first) - Report confidence levels alongside findings - Suppress findings below 0.4 confidence threshold - Always show fix snippets with recommendations - Frame savings as monthly recurring, not one-time