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 randommonicle/claude-skills --skill guard-the-spend-pathsgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/guard-the-spend-paths)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/guard-the-spend-paths"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/guard-the-spend-paths/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/randommonicle/claude-skills/guard-the-spend-paths"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/guard-the-spend-paths.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 | $0.00150 | $0.00650 |
| Opus 5 | $0.00075 | $0.00325 |
| Sonnet 5 | $0.00030 | $0.00130 |
| Haiku 4.5 | $0.00015 | $0.00065 |
Grade A, and why
guard-the-spend-paths 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guard the spend paths
From a public-facing AI site: the obvious LLM endpoint was capped, but the booking endpoints were not — an open invitation to slot-griefing by direct POST. And the controls that looked like defences were not: the origin allowlist failed open until its env var was set, and the storage token's auth failed open too, so a misconfiguration was invisible in the UI and discoverable only in function logs.
Rule 1 — cap every spend path at creation
Any endpoint that spends money (a paid model call, email, SMS, payment) or writes shared state (bookings, calendar slots, counters) gets a per-IP volume cap the day it is created, not when abuse appears. The UI is not a gate: anyone can POST directly in a loop. Rate-limiting is volume protection layered under auth and validation — it substitutes for neither.
Rule 2 — a fail-open guardrail is not a control until closed
For every control with a permissive default — an origin allowlist that permits when unset, an auth check that skips on a missing header, anything that warns and continues:
- Name the real primary defence. Until the fail-open control is closed, something else is doing the protecting (or nothing is). Say which, in the code or the config comment.
- Close it before launch, explicitly, and verify from the live surface that it now rejects (env-change-verification applies — setting the variable is not the control being live).
- Route its failures to logs or alerts. An inert guardrail looks healthy from the UI; only its own telemetry reveals it stopped guarding.
What this skill does not do
It does not cap internal fan-out (lock-at-the-chokepoint) and does not design auth. It ensures the money and shared-state surfaces have a working volume gate and that no inert control is being counted as a defence.
Why
An uncapped spend path is an open tap on the bill, and a fail-open guardrail is worse than none because it is counted as protection. Both failure modes are silent until the invoice or the incident. Evidence: ICC LESSONS_LEARNED L-001, L-006, L-007 (L-007 shared evidence with honest-failure-surfacing).
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 · 47 lines · 150 tokens per session scan A 4c26b5953234
guard-the-spend-paths is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 150 tokens to every session and 650 once invoked, about $0.0007 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.