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 revenium/openclaw-revenium --skill spike-findings-openclaw-reveniumgit clone --depth 1 https://github.com/revenium/openclaw-reveniumWrote 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/revenium/openclaw-revenium/spike-findings-openclaw-revenium)<a href="https://agentmods.dev/skills/revenium/openclaw-revenium/spike-findings-openclaw-revenium"><img src="https://agentmods.dev/badge/skills/revenium/openclaw-revenium/spike-findings-openclaw-revenium/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/revenium/openclaw-revenium/spike-findings-openclaw-revenium"><img src="https://agentmods.dev/badge/skills/revenium/openclaw-revenium/spike-findings-openclaw-revenium.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 | $0.00054 | $0.00877 |
| Opus 5 | $0.00027 | $0.00439 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
spike-findings-openclaw-revenium 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 12d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding optional NemoClaw / OpenShell support to the Revenium OpenClaw skill via a parallel
install path — deploying the budget-guardrail + metering skill into an OpenClaw agent running
under NemoClaw inside an OpenShell hardened sandbox, without disturbing the existing standalone
OpenClaw + Docker path. NemoClaw = orchestration/security layer (CLI nemoclaw); OpenShell = the
sandbox agents run inside.
Spike session wrapped: 2026-06-07. Validated live on Ubuntu host 34.224.27.67 (sandbox revenium-spike).
- Parallel install path only — the existing standalone OpenClaw + Docker path must remain untouched.
- Target host must be Linux + Docker (macOS unsupported); detect + refuse off-Linux explicitly (NemoClaw's installer graceful-skips on Darwin → false success).
- Build on NemoClaw's first-class CLI primitives (
skill install,policy-add,share mount,exec), not bespoke docker hacks. - Inside the sandbox, OpenClaw config/state is
/sandbox/.openclaw/(not~/.openclaw/). - Ship + apply a custom
reveniumegress policy (api.revenium.ai) — not allowed by default. - Metering runs host-side over a
share mount, not per-tickexecand not an in-sandbox cron. - The per-turn guardrail directive needs an OpenClaw plugin hook —
skill install/AGENTS.md do not deliver it.
<findings_index>
Feature Areas
| Area | Reference | Key Finding |
|---|---|---|
| Install & bootstrap | references/install-and-bootstrap.md | Linux-only; non-interactive env-var install; run detached to avoid apt SIGTTIN; ~11 min |
| Sandbox egress policies | references/sandbox-egress-policies.md | Deny-by-default proxy; ship + policy-add a host-scoped revenium preset for api.revenium.ai |
| Revenium CLI & metering | references/revenium-cli-and-metering.md | No Linux brew bottle → tarball install; SSL_CERT_FILE=/etc/openshell-tls/ca-bundle.pem; loop host-side via share mount, NOT per-tick exec |
| Skill deploy & enforcement | references/skill-deploy-and-enforcement.md | skill install gives discovery only; per-turn directive needs a plugin before_prompt_build hook — mechanism proven (spike 006), author from openclaw plugins init |
What ships with it
18 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.
- references/install-and-bootstrap.md 2.4 KB
- references/revenium-cli-and-metering.md 3.6 KB
- references/sandbox-egress-policies.md 2.4 KB
- references/skill-deploy-and-enforcement.md 2.8 KB
- sources/001-nemoclaw-bootstrap/probe-host-compat.sh 4.7 KB runs code
- sources/001-nemoclaw-bootstrap/README.md 8.2 KB
- sources/002-openshell-egress/README.md 5.0 KB
- sources/002-openshell-egress/revenium-policy.yaml 936 B
- sources/003-revenium-cli-in-sandbox/gh-release-policy.yaml 460 B
- sources/003-revenium-cli-in-sandbox/README.md 6.0 KB
- sources/004-background-metering-loop/README.md 5.9 KB
- sources/004-background-metering-loop/revenium-mount-tick.sh 847 B runs code
- sources/004-background-metering-loop/revenium-tick.sh 999 B runs code
- sources/005-skill-discovery-and-directives/README.md 5.7 KB
- sources/006-plugin-directive-injection/README.md 6.1 KB
- sources/006-plugin-directive-injection/revenium-guard/index.js 705 B runs code
- sources/006-plugin-directive-injection/revenium-guard/openclaw.plugin.json 314 B
- sources/006-plugin-directive-injection/revenium-guard/package.json 185 B
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.
- 12d ago First seen · 67 lines · 54 tokens per session scan A 59e8e72d9279
spike-findings-openclaw-revenium is a skill published in the GitHub repository revenium/openclaw-revenium (11 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 877 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…