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 christopherkarani/ryk --skill openclaw-plugingit clone --depth 1 https://github.com/christopherkarani/rykWrote 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/christopherkarani/ryk/openclaw-plugin)<a href="https://agentmods.dev/skills/christopherkarani/ryk/openclaw-plugin"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/openclaw-plugin/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/christopherkarani/ryk/openclaw-plugin"><img src="https://agentmods.dev/badge/skills/christopherkarani/ryk/openclaw-plugin.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 | $0.00000 | $0.00628 |
| Opus 5.5 | $0.00000 | $0.00251 |
| Sonnet 5.5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
openclaw-plugin 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ryk
ryk adds runtime guardrails to OpenClaw workflows via the ryk CLI. Use it when:
- You want policy-based command blocking before tool execution
- You need audit logging for agent sessions
- You want secret redaction in tool payloads
When to use ryk
| User intent | Use ryk? |
|---|---|
"Run rm -rf /" |
Yes — ryk blocks dangerous commands |
| "Let me run this shell script" | Yes — ryk evaluates against policy |
| "What time is it?" | No — safe query, no policy needed |
| "Execute this curl | sh pipe" | Yes — ryk blocks known dangerous patterns |
How it works
ryk registers lifecycle hooks that call the ryk CLI for policy decisions:
tool.before— evaluates tool calls against policy before executionsession.start,session.end— informational loggingtool.after— audit logging
If a tool is blocked, the plugin returns OpenClaw's terminal { block: true } result before execution. OpenClaw does not currently expose dedicated permission lifecycle hooks to this plugin; permission-like blocking is handled through tool.before before the tool call executes.
Prerequisites
- ryk CLI must be installed and available on
PATH - Run
ryk doctorto verify installation - Run
ryk agents setup openclaw, thenryk agents health openclaw --json
Example policy behavior
Safe command (git status):
{
"decision": "allow",
"risk": "low",
"reason": "policy_allow"
}
Dangerous command (rm -rf *):
{
"decision": "block",
"risk": "high",
"reason": "policy_deny",
"message": "Blocked by ryk policy"
}
Key behaviors
- Thin wrapper: All policy decisions are made by the ryk CLI
- No duplicated logic: The plugin does not reimplement policy
- Secret redaction: Keys matching
password,token,secret,api_keyare replaced with[REDACTED]before sending to ryk - Fail closed in full runtime: If the ryk CLI is missing or cannot be attested, the plugin registers a blocking
before_tool_callveto - Inert dispatcher canary:
ryk_openclaw_canaryproves the Gateway tool path with a nonce-bound Ryk denial and never executes its input - Honest limits: Hooks are advisory; the strongest protection is
ryk run -- openclaw
What ships with it
10 files 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.
- 1mo ago First seen · 69 lines · 0 tokens per session scan E 1de8509fcd87
openclaw-plugin is a skill published in the GitHub repository christopherkarani/ryk (42 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 628 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 2026-08-30.
Other skills, from other repositories
beacon-memory-distill
Turn recorded agent sessions (Beacon traces from Claude Code, Cursor, Codex, OpenCode, and other harnesses) into reviewed, reusable project memory. Scores selected traces, reads the source trace behind each high-signal candidate, drafts a grounded lesson, and approves it only after the user confirms. Use when the user…
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.
blueprint-work-order
Create a work-order for isolated subagent execution, optionally linked to a GitHub issue. Use when breaking a PRP into delegatable tasks or spawning from an issue.