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 agentmods add skills/luongnv89/asm/runtime-budget-failnpx skills add luongnv89/asm --skill runtime-budget-failgit clone --depth 1 https://github.com/luongnv89/asmWrote 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/luongnv89/asm/runtime-budget-fail)<a href="https://agentmods.dev/skills/luongnv89/asm/runtime-budget-fail"><img src="https://agentmods.dev/badge/skills/luongnv89/asm/runtime-budget-fail.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00064 |
| Opus 5 | $0.00019 | $0.00032 |
| Sonnet 5 | $0.00008 | $0.00013 |
| Haiku 4.5 | $0.00004 | $0.00006 |
Grade A, and why
runtime-budget-fail 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 4d 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.
The source is not reproduced here
Licensed MIT
The repository is licensed MIT, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 4d ago First seen · 8 lines · 39 tokens per session scan A aa35c2ab1e2b
runtime-budget-fail is a skill published in the GitHub repository luongnv89/asm (908 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 64 once invoked, about $0.0002 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
experiment-design-and-ab-testing
Guides the product-experimentation layer of A/B testing — writing a falsifiable hypothesis, sizing a test with minimum detectable effect (MDE), reading statistical significance without falling into the peeking problem, accounting for the novelty effect, and choosing guardrail metrics. Use when the user asks to "design…
data-retention-and-privacy-by-design
Use when the user asks to "design a new data model that stores personal data", "add a retention policy", "figure out how long to keep guest data", "handle a data deletion request", "design for GDPR compliance", or is adding any field/table that captures a name, email, phone, ID document, or payment detail. Guides…
engineering-values-and-tradeoff-principles
Use when the user asks to "should we prioritize shipping fast or reliability here", "define an error budget", "how much risk can we take on this release", "we keep debating speed vs quality", "write down our engineering principles", or is deciding how to balance reliability/velocity/quality tradeoffs at a policy level…
cloudbase-wechat-integration
CloudBase WeChat integration guide for Mini Program WeChat Pay, Official Account JSAPI Pay, Native QR-code Pay, Official Account OAuth, openid handling, payment callbacks, and CloudBase Integration Center generated functions. This skill should be used when users ask to add, debug, or extend WeChat payment or…
idempotency-and-retry-safety
Use when the user asks to "make this endpoint safe to retry", "add an idempotency key", "handle duplicate webhook delivery", "design a payment/booking API", "what happens if this request is sent twice", or is building any endpoint or message consumer that a client, queue, or upstream system might call more than once…
security-and-hardening
Hardens a feature against attack before or while it's built — threat-model trust boundaries with STRIDE, apply the Always/Ask-First/Never tiers, and prevent OWASP Top 10 classes by construction. Use when building anything that accepts user input, handles auth, sessions, file uploads, webhooks, payments, PII, or calls…