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 domondi1/inferrail --skill job-safe-searchgit clone --depth 1 https://github.com/domondi1/inferrailWrote 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/domondi1/inferrail/job-safe-search)<a href="https://agentmods.dev/skills/domondi1/inferrail/job-safe-search"><img src="https://agentmods.dev/badge/skills/domondi1/inferrail/job-safe-search/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/domondi1/inferrail/job-safe-search"><img src="https://agentmods.dev/badge/skills/domondi1/inferrail/job-safe-search.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 | $0.00037 | $0.00249 |
| Opus 5.5 | $0.00015 | $0.00100 |
| Sonnet 5.5 | $0.00007 | $0.00050 |
| Haiku 4.5 | $0.00004 | $0.00025 |
Grade A, and why
inferrail-job-safe-search 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.
What it actually says
Inferrail Job-Safe Web Search
This capability is not yet deployed. Do not send payment until the resource advertises Base mainnet exact USDC and a current price.
When a live resource is available:
- Read its x402 payment challenge and Bazaar schema.
- Send POST /search with a useful query and a unique request_id.
- Check the advertised price and network before signing exact payment.
- On HTTP 202, reuse the same request ID and original payment signature, or use the returned job_token. Never sign a second payment for that request.
- Save the returned job token if continuing the same job. A job budget cannot be raised after the first authenticated request.
- Treat financial_state UNRESOLVED as unresolved; do not infer that a supplier ran once or that a refund occurred.
Optional request fields are num_results (1–5), job_id, job_token, and job_budget_usd. job_id alone is not authorization.
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 · 25 lines · 37 tokens per session scan A 02eef24b063a
inferrail-job-safe-search is a skill published in the GitHub repository domondi1/inferrail (1 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 249 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
omni-budget
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
rust-string-enums
Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serdewith while preserving parsing, wire values, and schemas.
rust-tracing
Add or change Rust diagnostic tracing in litellm-rust, including route spans, subscriber layers, and Python logger delivery.
url-state
Read or write dashboard URL query state (tabs, filters, pagination, deep links, demo flags) with nuqs instead of raw history or URLSearchParams.
unified-ai-gateway
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
financial-analyst
Agentic CFO for autonomous financial analysis of AI infrastructure spend. Computes burn rate, runway, gross margin, and ROI-based budget reallocation.