oc-security

oc-security is a command for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 0 tokens per session (419 once invoked), scanned A, original, MIT.

A command that checks an OpenClaw installation for security problems and groups the results by seriousness.

In plain words
What is it for?
Running normal or deeper audits, including a live Gateway check, displaying critical and lower-risk findings, applying supported fixes, and producing JSON for scripts.
Why use it?
It makes security findings easier to review and can automatically fix supported issues when requested.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Running normal or deeper audits, including a live Gateway check, displaying critical and lower-risk findings, applying supported fixes, and producing JSON for scripts.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/theophiluschinomona/claude-openclaw-plugin/oc-security
Install

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.

Clone the repo
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-plugin

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

Wrote 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.

agentmods badge for oc-security

README.md
[![agentmods](https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-security/github.svg)](https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-security)
Your own site
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-security"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-security/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.

agentmods 80×15 button for oc-security

Your own site · 80×15
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-security"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00419
Opus 5 $0.00000 $0.00210
Sonnet 5 $0.00000 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured 9d ago against content hash c5e320a82e48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

oc-security 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 9d 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.

plugins/openclaw/commands/oc-security.md · 73 lines

What it actually says

/oc-security Command

Run an OpenClaw security audit, group findings by severity, and optionally auto-fix issues.

Arguments

The user provides: $ARGUMENTS

Parse optional flags:

  • --deep — include live Gateway probe
  • --fix — auto-fix supported findings
  • --json — output raw JSON (for scripting)

Execution

  1. Run the security audit:
openclaw security audit $ARGUMENTS
  1. Parse and group findings by severity:

CRITICAL

Show critical findings first with red emphasis. For each:

  • Finding: description of the issue
  • Risk: why it matters
  • Fix: exact command or config change to resolve

WARNING

Show warnings next. Same format as critical but lower urgency.

INFO

Show informational items last. Brief description + recommendation.

  1. After showing findings, provide a summary:
Security Audit Summary:
  Critical: X findings
  Warning:  Y findings
  Info:     Z findings
  1. If --fix was used, report which fixes were applied automatically.

If No Findings

Report a clean audit:

✓ Security audit passed — no findings.

Suggest running --deep for a more thorough check.

If OpenClaw Not Installed

Guide the user to install OpenClaw first:

OpenClaw CLI not found. Run /oc-setup to install.

After Running

  • For critical findings: urge immediate action, offer to apply fixes
  • For --fix: verify fixes with a re-run: openclaw security audit
  • Suggest scheduling periodic audits (e.g., after config changes or updates)
  • For hardening guidance: reference the openclaw-security skill
Changes

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.

  1. 9d ago First seen · 73 lines · 0 tokens per session scan A c5e320a82e48

Subscribe to this mod's changes

oc-security is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 419 tokens. 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.