Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TheophilusChinomona/claude-openclaw-plugin --skill openclaw-autonomy-auditgit clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-autonomy-audit)<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-autonomy-audit"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-autonomy-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-autonomy-audit"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-autonomy-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01903 |
| Opus 5 | $0.00026 | $0.00951 |
| Sonnet 5 | $0.00010 | $0.00381 |
| Haiku 4.5 | $0.00005 | $0.00190 |
Grade A, and why
openclaw-autonomy-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomy Audit (OpenClaw)
Assess whether an OpenClaw agent can operate independently between user interactions and produce a scored remediation plan.
Canonical references
- Remediation patterns and templates: Read
references/autonomy-patterns.md - Cron/heartbeat setup: cross-reference openclaw-automation skill
- Agent workspace files: cross-reference openclaw-agent-builder skill
- Cron management command:
/oc-cron
The Five Critical Layers of Agent Autonomy
True autonomous operation requires all five layers working together. A gap in any single layer breaks the chain.
Layer 5: Monitoring ← Can you tell if it's working?
Layer 4: Error Handling ← Can it recover from failures?
Layer 3: Process Mgmt ← Does it stay alive?
Layer 2: Decision Logic ← Does it know what to do when idle?
Layer 1: Scheduling ← Does anything wake it up?
| Layer | What It Provides | Key Files/Config |
|---|---|---|
| 1. Scheduling | Periodic wake-up triggers | openclaw cron list, heartbeat config |
| 2. Decision Logic | Explicit "when idle, do X" rules | SOUL.md — ## Autonomous Behavior section |
| 3. Process Management | Gateway stays alive without supervision | launchd / systemd / pm2 daemon config |
| 4. Error Handling | Retry limits, cost caps, loop breakers | AGENTS.md — ## Cost Controls, SOUL.md guardrails |
| 5. Monitoring | Health checks, structured logging | Health-check cron job, cron.runLog, memory/ directory |
Autonomy Maturity Scoring Rubric
Score each item 0–2. Maximum score: 16.
| # | Check | 0 (Missing) | 1 (Partial) | 2 (Complete) |
|---|---|---|---|---|
| 1 | SOUL.md autonomous behavior rules | No autonomous behavior section | Has section but vague ("be helpful") | Explicit idle triggers: "when idle, do X", "every N minutes, check Y" |
| 2 | Scheduling mechanism | No cron jobs, no heartbeat | Has cron OR heartbeat but not both | Cron for clockwork tasks + heartbeat for judgment-based tasks |
| 3 | HEARTBEAT.md actionable checklist | Empty or missing | Has content but no - [ ] checklist items |
Mission-specific checklist items with clear done criteria |
| 4 | Session clearing strategy | No session reset config | Has reset but no retention policy | session.reset + cron.sessionRetention configured |
| 5 | Gateway daemon persistence | Manual openclaw gateway start only |
Has daemon but no auto-restart | launchd/systemd/pm2 with auto-restart on failure |
| 6 | Error handling / cost controls | No limits anywhere | Has max-iteration OR retry limits | Max turns, max retries, explicit stop conditions, cost cap in AGENTS.md |
| 7 | Health monitoring | No health checks | Health check exists but interval > 5min | Health-check cron at <= 5min checking gateway + cron + channels |
| 8 | Structured activity logging | No logging config | Has cron.runLog OR memory/ dir |
cron.runLog enabled + agent writes daily memory/YYYY-MM-DD.md entries |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 137 lines · 52 tokens per session scan A a5678e16d2ab
openclaw-autonomy-audit is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,903 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…