What makes OpenClaw Waste Audit notable?

1.4K downloads. Trust evidence available

How should OpenClaw Waste Audit be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

OpenClaw Waste Audit

Find recurring OpenClaw jobs that may be wasting tokens before the waste compounds. Read-only by default. Gives evidence and a copy-paste agent prompt for sa... Skill: OpenClaw Waste Audit Owner: choosenobody Summary: Find recurring OpenClaw jobs that may be wasting tokens before the waste compounds. Read-only by default. Gives evidence and a copy-paste agent prompt for sa... Tags: audit:1.4.2, cost:1.4.2, cron:1.4.2, latest:1.8.12, openclaw:1.4.2, read-only:1.4.2, token:1.4.2, token-save:1.4.2, waste:1.4.2 Version history: v1.8.12 | 2026-05-29T12:38:23.191Z | user Added Whe

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

1.8.12

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 1.8.12release · observed May 29, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179c00gh3examr898mcx3adts86vzhf:waste-audit

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-choosenobody-waste-audit/snapshot"

Documentation

CLAWHUB

122,748 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: waste-audit
description: "Find recurring OpenClaw jobs that may be wasting tokens before the waste compounds. Read-only by default. Gives evidence and a copy-paste agent prompt for safe manual verification."
version: 1.8.12
platforms: [linux, macos, windows]
metadata:
hermes:
tags: [openclaw, tokensave, cron, waste, audit, tokens]
related_skills: []
---

## Features

- 🔍 Recurring Waste Detection: Finds recurring OpenClaw jobs that may be wasting tokens.
- 📊 Token Burn Ranking: Ranks likely waste candidates by recurring usage, errors, and delivery signals.
- 🧾 Evidence Summary: Shows why a job was flagged before suggesting action.
- 🛠 Manual Verification Prompt: Gives a copy-paste prompt for safe agent-side verification.
- 🔒 Read-Only Safety: Does not edit, disable, delete, upload, or auto-fix jobs.

## Install

For shared OpenClaw agents, install into the global managed skills directory:

```bash
openclaw skills install waste-audit --global
```

To upgrade an existing shared install:

```bash
openclaw skills install waste-audit --global --force
```

Then test with:

```bash
check openclaw waste
```

## Activation

Primary activation phrase:

```
check openclaw waste
```

Do not use this for general OpenClaw setup, gateway debugging, provider configuration, or normal job management.

## Where This Fits

This skill is the OpenClaw-specific starting point for agent token waste auditing.
Use it when you want to inspect recurring OpenClaw jobs for possible token waste.
For broader model routing, sub-agent routing, fallback, retry, or cross-agent runtime analysis, use a separate Agent Routing Waste Audit workflow instead. This skill should not be treated as a generic routing optimizer.

## What You Will Get

**1. Fix First**

Include:

- Job
- Why it looks wasteful
- Evidence
- Confidence: High / Medium / Low
- Recommended manual action

**2. Top Waste Candidates**

List up to 5 candidates.

For each candidate, include:

- Job
- Waste signal
- Evidence
- Why it matters

**3. Manual Verification Prompt**

A ready-to-copy prompt for your agent.

```
Please inspect this recurring OpenClaw job for possible token waste.

Job: <job name>
Reason it was flagged: <short reason>
Evidence: <schedule, runs checked, tokens used, error rate, delivery/summary signal>

Please verify whether this job is still useful.

Do not edit, disable, delete, or mutate anything yet.

First explain:
1. whether this is real waste,
2. what caused it,
3. the safest manual next step,
4. what evidence I should check before changing anything.

Redact secrets and do not expose private payloads.
```

If any candidate looks important but you are not sure whether it is real waste, send only the "Top Waste Candidates" section to @BeeGeeEth on X. Do not include secrets, API keys, private logs, wallet data, full config files, or production credentials.

## Related Next Step

If this audit finds a job where the main issue appears to be model choice, retry behavior, fall

_meta.json

{
  "ownerId": "kn7aeqth7vtkece5j16y05y1sn86vga3",
  "slug": "waste-audit",
  "version": "1.8.12",
  "publishedAt": 1780058303191
}

references/openclaw-waste-patterns.md

# OpenClaw Waste Audit — Reference Bank

## Observed Waste Patterns

### Pattern 1: Health Probe Loop (D8 CLEAN_LOOP)
- Job: Health monitoring job — high run count, 0% errors, 0% delivered
- Model: actual model from `payload.model` in jobs.json (not EXEC_SCRIPT tag)
- Frequency: hourly or more frequent
- Signature: `delivered=false` + `status=ok` + repetitive "all clear" summaries — structurally silent, zero external value
- Signal: EXEC_SCRIPT tag ≠ bash. Always check `payload.model` in jobs.json.
- Verdict: No delivery means output is discarded. Zero value despite 100% success rate.

### Pattern 2: Zero-Value Log Verification
- Job: Log analyzer job — runs but log format doesn't match parser
- Latest summary: "ERROR: 0 | WARN: 0" — job runs successfully but produces nothing useful
- Frequency: every 6h or more frequent — excessive for zero-value output
- Signal: Both wrong frequency AND wrong logic. Double waste.
- Critical signal: `delivered=false` + zero content = structural failure, not just over-scheduling.

### Pattern 3: High-Frequency Midnight Burner
- Job: Embedding/job scheduled 4x/day at midnight hours
- Signal: Midnight runs unlikely to need human attention anyway
- Verdict: 4x/day is excessive. 1x or 2x sufficient.

### Pattern 4: tmp-auto-cleanup (Hybrid Failure + Silent)
- Job: cleanup job with intermittent output
- Frequency: every 4h or more
- Signal: Mix of `status=error` and `status=ok` with `(no output)` — unreliable execution
- Delivered: false
- Problem: 50% error rate + 50% silent success = no reliable output ever delivered

### Pattern 5: Disk/Memory Monitor (UNCLEAR + No Delivery)
- Jobs: monitor-type jobs (disk, memory, etc.)
- Frequency: every 6h or daily
- Problem: Classified UNCLEAR, delivered=false, no visible value
- Rule of thumb: Any monitor job with delivered=false and no external target is waste by definition

## Diagnostic Command Cheatsheet

```bash
# Run ClawSetup diagnostic (primary in this env — always available)
python3 ~/.hermes/scripts/clawsetup_diagnostic.py

# Get top 10 by token burn
python3 ~/.hermes/scripts/clawsetup_diagnostic.py 2>&1 | grep -A12 "TOP 10"

# List all jobs with model info from jobs.json
cat ~/.openclaw/cron/jobs.json | python3 -c "
import json,sys
d=json.load(sys.stdin)
for j in d.get('jobs',[]):
    model=j.get('payload',{}).get('model','null')
    if model and model not in ('null','None',''):
        print(f'{j[\"name\"]}: {model}')
"

# Check actual token burn from JSONL runs (use usage.total_tokens, NOT top-level totalTokens)
python3 -c "
import json, glob, os
runs_dir = os.environ.get('OPENCLAW_HOME', os.path.expanduser('~/.openclaw'))
runs_dir = os.path.join(runs_dir, 'cron', 'runs')
for f in glob.glob(f'{runs_dir}/*.jsonl'):
    total = 0
    count = 0
    with open(f) as fh:
        for line in fh:
            try:
                d = json.loads(line)
                total += d.get('usage',{}).get('total_tokens',0)
                count += 1
            except: pass
    if

skill-card.md

## Description:

Find recurring OpenClaw jobs that may be wasting tokens before the waste compounds.

This skill is ready for commercial/non-commercial use.

## Publisher:

[choosenobody](https://clawhub.ai/user/choosenobody)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operators use this skill to audit recurring OpenClaw jobs for likely token waste, review evidence, and prepare a safe manual verification prompt before changing schedules, prompts, or configuration.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill includes guidance to share uncertain audit findings with a hard-coded X account, which could expose operational details if followed without reviewing the exact payload.

Mitigation: Keep audit results local unless the user explicitly reviews and approves the exact information to share; remove or ignore the hard-coded contact instruction before installation.

Risk: Audit evidence can include private job names, summaries, logs, paths, credentials, or other sensitive operational context.

Mitigation: Redact secrets and private payload details before displaying or sharing findings, and use placeholders for credentials, tokens, wallet data, private logs, and production configuration.

Risk: A recurring job may be useful even when it looks wasteful from run count, delivery, error, or summary-length signals.

Mitigation: Require manual verification before changing a job schedule, prompt, model policy, or configuration, and present confidence and evidence with each recommendation.

## Reference(s):

- [OpenClaw Waste Audit reference bank](artifact/references/openclaw-waste-patterns.md)
- [ClawHub skill page](https://clawhub.ai/choosenobody/skills/waste-audit)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, guidance]

**Output Format:** [Markdown audit report with evidence summaries, ranked candidates, diagnostic commands, and a copy-paste manual verification prompt.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Read-only recommendations; no automatic job edits, disabling, deletion, uploads, or fixes.]

## Skill Version(s):

1.8.12 (source: release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 21h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.