Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Token Optimizer for OpenClaw
You are a token optimization expert. Audit the user's OpenClaw agent setup, detect waste patterns, and provide actionable fixes with dollar savings.
## Workflow
### Phase 0: Detect + Scan
Run the scan to collect session data:
```bash
npx token-optimizer scan --days 30
```
If no sessions found, tell the user and stop. Otherwise, report the scan summary (agents, sessions, total cost).
### Phase 1: Audit
Run the full waste detection:
```bash
npx token-optimizer audit --days 30
```
Present findings grouped by severity. For each finding:
1. Name the pattern (e.g., "Heartbeat Model Waste")
2. Explain what's happening in plain language
3. Show the monthly $ waste
4. Give the exact fix
### Phase 2: Coaching
For each finding, explain WHY it matters:
- **Heartbeat Model Waste**: "Your cron agent is using Sonnet to check if there's work. That's like hiring a surgeon to take your temperature."
- **Empty Heartbeat Runs**: "Your agent loads 50K tokens of context, finds nothing to do, and exits. That's $X/month to stare at an empty inbox."
…
The line at the top of this page pins the label git:20260316.25fde7b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1921 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
alexgreensh/token-optimizer · 2,920 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_atan5delpxhdjyyq
GET https://markdownregistry.com/api/v1/resolve?ref=alexgreensh/token-optimizer/token-optimizer
GET https://markdownregistry.com/api/v1/blob/3deed339f2e374214f6c96c03d492757ec98db36774b6a7303f32f2c430d8f01
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
alexgreensh/token-optimizer · cowork/token-optimizer/skills/fleet-auditor/SKILL.md · Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when…
alexgreensh/token-optimizer · cowork/token-optimizer/skills/resume-checkpoint/SKILL.md · Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work…
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-dashboard/SKILL.md · Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the…
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
alexgreensh/token-optimizer · devin/SKILL.md · Explicitly filter private captured command output using Token Optimizer. Works on its own or as the manual fallback to…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/fleet-auditor/SKILL.md · Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/resume-checkpoint/SKILL.md · Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-dashboard/SKILL.md · Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
alexgreensh/token-optimizer · skills/fleet-auditor/SKILL.md · Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when…
alexgreensh/token-optimizer · skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
nitinjain999/platform-skills · skills/token-optimizer/SKILL.md · Route broad repository discovery to a cheaper worker model using each client's native subagents, keeping the main agent…
nitinjain999/platform-skills · plugins/platform-skills/skills/token-optimizer/SKILL.md · Route broad repository discovery to a cheaper worker model using each client's native subagents, keeping the main agent…
jnpiyush/agentx · .github/skills/development/token-optimizer/SKILL.md · Use when managing instruction/context budgets, cache-aware tokenomics and cost estimates while preserving acceptance…