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 ertugrulakben/cashclaw --skill cashclaw-guardgit clone --depth 1 https://github.com/ertugrulakben/cashclawWrote 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/ertugrulakben/cashclaw/cashclaw-guard)<a href="https://agentmods.dev/skills/ertugrulakben/cashclaw/cashclaw-guard"><img src="https://agentmods.dev/badge/skills/ertugrulakben/cashclaw/cashclaw-guard/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/ertugrulakben/cashclaw/cashclaw-guard"><img src="https://agentmods.dev/badge/skills/ertugrulakben/cashclaw/cashclaw-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 100 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00055 | $0.01538 |
| Opus 5 | $0.00028 | $0.00769 |
| Sonnet 5 | $0.00011 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
cashclaw-guard 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 13d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CashClaw Guard
Agent runtime protection. Stop $34K incidents in 12 lines of code.
When an AI agent runs unattended, two things can break the bank in one night:
- Cost runaway — a misconfigured loop calls the LLM API thousands of times before the soft limit kicks in 24 hours later.
- Sonsuz döngü — agent calls itself, or two agents call each other, with no exit condition.
Cloudflare lost $34,000 in 8 days to a Durable Object loop in February 2026. The fix wasn't a smarter agent — it was a runtime layer that says "no, you've spent enough."
CashClaw Guard is that layer. It plugs into any OpenClaw-compatible agent and enforces a YAML policy at every LLM call and tool invocation.
Why this skill?
| Tool | Watches | Enforces |
|---|---|---|
| Helicone, Langfuse | ✅ | ❌ |
| Datadog, Sentry | ✅ | ❌ |
| OpenAI soft limits | ✅ (24h delay) | ⚠️ partial |
| CashClaw Guard | ✅ | ✅ real-time, hard cap |
Pricing Tiers
| Tier | Scope | Price | Delivery |
|---|---|---|---|
| Audit | Policy review + recommended config for 1 agent | $19 | 24h |
| Setup | Full deploy: install, YAML policy, webhook hookup, dashboard | $49 | 48h |
| Hardening | Audit + custom rate limits + multi-agent + on-call runbook | $99 | 5d |
Quick Start
npm install cashclaw
cashclaw guard init
# edit ~/.cashclaw/guard-policy.yaml
cashclaw guard test
SDK
import { guard } from 'cashclaw/guard';
// Wrap any LLM call
const safeChat = guard.llm({
maxCostUsd: 5,
maxTokens: 50000,
model: 'gpt-5.5',
agentId: 'support-bot',
})(async (prompt) => {
return await openai.chat.completions.create({
model: 'gpt-5.5',
messages: [{ role: 'user', content: prompt }],
});
});
await safeChat('summarize this ticket');
// → throws BudgetExceeded if the call would push you over the cap
// → throws RecursionKilled if the same fingerprint repeats 5x in 60s
// → fires Telegram alert before throwing
// Tool firewall (called before any shell / api / mcp invocation)
import { guard } from 'cashclaw/guard';
guard.tool('slack.send', { agentId: 'support-bot' });
// throws ToolDenied if slack.send isn't in the allowlist
// throws RateLimitExceeded if rate per minute/hour is hit
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.
- 13d ago First seen · 175 lines · 55 tokens per session scan A 7846c9569910
cashclaw-guard is a skill published in the GitHub repository ertugrulakben/cashclaw (300 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,538 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
medium-strategy
Use when planning Medium as a growth and revenue system over months rather than one post — the Partner Program, solo profile versus starting or pitching a publication, engineering for Boost and the distribution tiers, tag and topic choices for reach, and a canonical cross-posting plan, read from and written back to…
ccs
Search local Claude Code, Codex, and Cursor user-prompt history (read-only). Use when you need a past prompt, want to grep coding-agent session text, or pipe prompt history as JSON.
agentx
Drive X/Twitter from the CLI (read, post, DM, lists, communities, Grok, scheduling, analytics). Use when an agent needs to read or act on X/Twitter. Every command prints one JSON envelope.
monetization
Estrategia e implementacao de monetizacao para produtos digitais - Stripe, subscriptions, pricing experiments, freemium, upgrade flows, churn prevention, revenue optimization e modelos de negocio SaaS.
build-feature
Full pipeline: evaluation -> spec -> implementation -> review -> QA.
council
Convenes multiple agents to debate an important decision.