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 adamjali/claude-skills --skill jina-image-searchgit clone --depth 1 https://github.com/adamjali/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/adamjali/claude-skills/jina-image-search)<a href="https://agentmods.dev/skills/adamjali/claude-skills/jina-image-search"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/jina-image-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/adamjali/claude-skills/jina-image-search"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/jina-image-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 | $0.00061 | $0.01299 |
| Opus 5 | $0.00030 | $0.00649 |
| Sonnet 5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
jina-image-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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://s.jina.ai/?q=unsplash+mountains+landscape" \ How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jina AI Image Search & Web Scraping
<execution_context>
- 🟢 Auto-execute: search, scrape, parse, return URLs
- Stateless — no history file, no recovery
- Auth: Bearer token read from the
JINA_API_KEYenvironment variable </execution_context>
Overview
Jina AI provides two endpoints:
- s.jina.ai - Search the web and return structured results
- r.jina.ai - Scrape any URL and convert to GitHub-flavored markdown with embedded images
Authentication
This skill reads your Jina key from the JINA_API_KEY environment variable. Get a free key at https://jina.ai (no credit card; a new email address gets a fresh free token grant). Then set it in your shell profile:
export JINA_API_KEY="your-key"
Send it as a Bearer token:
Authorization: Bearer $JINA_API_KEY
Free no-key fallback (verified 2026-06)
If the key returns 402 (InsufficientBalanceError = balance exhausted), or to avoid spending it:
- Reader
r.jina.aiworks WITHOUT a key — drop theAuthorizationheader (free, per-IP rate-limited). Use it to scrape/read a page; its clean-markdown output often beats Claude Code's built-inWebFetch, so prefer it (or use both). - Search
s.jina.aiREQUIRES a key (keyless = 401). When the key is dead, do the search half with Claude Code's built-inWebSearchtool (no key, no cost), then scrape the chosen URLs with keylessr.jina.ai. - The 402 is tied to the key's balance, not your IP, so keyless Reader works even when the key is broke.
Recovery order: (1) reads → keyless Reader; (2) search → built-in WebSearch, or mint a fresh free key at https://jina.ai and update JINA_API_KEY; (3) pay to top up only as a last resort.
Image Search Workflow
Step 1: Search for Images
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 132 lines · 61 tokens per session scan A 55d3864a7ffc
jina-image-search is a skill published in the GitHub repository adamjali/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,299 once invoked, about $0.0003 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
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
ignore-setup
Set up a project so Claude stops discovering lockfiles, generated code, minified assets and binaries on every search — a managed .ignore, the Glob setting that makes Glob obey it, and a short read-deny list for secrets. Use when someone asks for a .claudeignore, asks to exclude files from the context, says Claude…
plugin-commands
Commands for validating, testing, iterating on, and releasing plugins in this marketplace (claude-toolbelt) — plugin validate, watcher-parity check, eval, --plugin-dir dev loop, plugin tag. Use when validating a plugin before pushing, running skill evals, developing a plugin without touching the installed cache, or…
commit
Create a single well-crafted git commit from current changes. Analyzes diff, follows repo's commit style, and writes a concise "why not what" message.