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 mydisha/keirouter --skill keirouter-web-searchgit clone --depth 1 https://github.com/mydisha/keirouterWrote 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/mydisha/keirouter/keirouter-web-search)<a href="https://agentmods.dev/skills/mydisha/keirouter/keirouter-web-search"><img src="https://agentmods.dev/badge/skills/mydisha/keirouter/keirouter-web-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/mydisha/keirouter/keirouter-web-search"><img src="https://agentmods.dev/badge/skills/mydisha/keirouter/keirouter-web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Data Exfiltration · line 35 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00051 | $0.00711 |
| Opus 5.5 | $0.00020 | $0.00284 |
| Sonnet 5.5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
keirouter-web-search scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl $KEIROUTER_URL/v1/models/search | jq '.data[].id' How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KeiRouter — Web Search
Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.
Discover
curl $KEIROUTER_URL/v1/models/search | jq '.data[].id'
curl "$KEIROUTER_URL/v1/models/info?id=tavily/tavily-search"
model is provider/model (e.g. tavily/tavily-search), a chain name that lists several search providers for automatic fallback, or an alias.
Endpoint
POST $KEIROUTER_URL/v1/search
| Field | Required | Notes |
|---|---|---|
model |
yes | from /v1/models/search |
query |
yes | search query |
max_results |
no | number of results (provider default when omitted) |
search_type |
no | web (default) or news, where the provider supports it |
Examples
curl -X POST $KEIROUTER_URL/v1/search \
-H "Authorization: Bearer $KEIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tavily/tavily-search","query":"KeiRouter open source","max_results":5}'
JS:
const r = await fetch(`${process.env.KEIROUTER_URL}/v1/search`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.KEIROUTER_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({ model: "brave-search/brave-search", query: "latest LLM benchmarks", max_results: 10 }),
});
const { results } = await r.json();
for (const hit of results) console.log(hit.title, hit.url);
Response shape
{
"query": "KeiRouter open source",
"results": [
{ "title": "...", "url": "https://...", "snippet": "...", "score": 0.92 }
]
}
snippet and score are omitted when the provider doesn't return them. The X-KeiRouter-Provider header names the provider that answered.
Provider quick reference
| Provider | model |
Notes |
|---|---|---|
| Tavily | tavily/tavily-search |
Also does web fetch |
| Exa | exa/exa-search |
Also does web fetch |
| Brave Search | brave-search/brave-search |
|
| Serper | serper/serper-search |
Google results |
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 Changed · -15 lines · -12 tokens per session 995b47ba86a1
- 1mo ago First seen · 89 lines · 63 tokens per session scan A 124b3c75b2c8
keirouter-web-search is a skill published in the GitHub repository mydisha/keirouter (154 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 711 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
10router-web-fetch
Fetch URL → markdown / text / HTML via 10Router /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
caveman-discover
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
caveman-optimize
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
cavecrew
When to delegate to cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit) or cavecrew-reviewer (diff review) instead of working inline or using Explore. Their output is compressed, so main context lasts longer.
caveman-evidence-review
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.