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/jxoesneon/ciel/web_fetchnpx skills add jxoesneon/Ciel --skill web_fetchgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/web_fetch)<a href="https://agentmods.dev/skills/jxoesneon/ciel/web_fetch"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/web_fetch.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 | $0.00017 | $0.00307 |
| Opus 5 | $0.00009 | $0.00153 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
web_fetch 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
triggers: [fetch, download, curl, get url, visit] What it actually says
web_fetch
Fetch a URL.
Operations
fetch.get(url, headers?)— returns body + metadata + fetch_hash.fetch.json(url)— parsed JSON.fetch.md(url)— HTML→markdown extraction.fetch.paginate(url, pattern)— follow next links.
I/O Contract
io_contract:
input: { url, "headers?", "timeout_s?" }
output: { status, body, headers, fetch_hash, final_url }
idempotent: true
side_effects: [network]
Safety
- Robots.txt respected.
- Redirects capped at 10.
- Body size capped by
acquisition.config.total_wall_budget_sproxy (configurable). - All fetches logged with URL hashed if
redact_urls: true. - Bodies stored in MemPalace by
fetch_hashfor audit.
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 · 42 lines · 17 tokens per session scan A ae0d95605031
web_fetch is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 307 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
screenshot-automation
Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.
canonical-tag-auditor
Technical debt is invisible until traffic drops. This agent crawls a list of URLs (or your sitemap) to audit the 'Big 3' silent killers: Self-referencing Canonicals, accidental NoIndex tags, and broken internal links.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
tavily-usage
This skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily search", "scrape this website", "get information from this link", or "web search for X".
browser-cdp
Native CDP browser automation reference. Headless/headed Chrome control, screenshots, JS evaluation. (/browser-cdp, browser automation, cdp, scraping).
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.