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 3338902669-ops/agent-orchestra --skill image-searchgit clone --depth 1 https://github.com/3338902669-ops/agent-orchestraWrote 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/3338902669-ops/agent-orchestra/image-search)<a href="https://agentmods.dev/skills/3338902669-ops/agent-orchestra/image-search"><img src="https://agentmods.dev/badge/skills/3338902669-ops/agent-orchestra/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/3338902669-ops/agent-orchestra/image-search"><img src="https://agentmods.dev/badge/skills/3338902669-ops/agent-orchestra/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 | $0.00033 | $0.00611 |
| Opus 5.5 | $0.00013 | $0.00244 |
| Sonnet 5.5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
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 8d 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 -fsSLI -A 'Mozilla/5.0' -H 'Accept: image/png,image/jpeg,image/gif,image/webp,image/*;q=0.5' -H 'Referer: <any-https-origin-that-is-not-the-image-host>' '<image-url>' How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Search
Purpose
Find public images by text query and return their URLs plus source pages. Text-to-image search only — never use it to identify a person from a supplied photograph.
Tooling
Bundled CLI (Hatch runtime):
/opt/hatch/bin/image-search "<query>" --max-results 5 [--language <code>]
Output is JSON: {provider, query, request_id, results: [...]}. Each result carries:
media_url— preferred full-image URL when present.thumbnail_cdn_url— renderable CDN preview; fallback whenmedia_urlis absent. Treat as cache, not durable storage.page_url— source page; keep for provenance/attribution.media_handle,candidate_ref— internal, non-renderable. Never fetch or display.
Only results with media_url or thumbnail_cdn_url are returned. Pick the best match, not blindly the first.
If the CLI is absent on your runtime, reimplement the same JSON contract against any image-search backend before using this skill.
Operating Rules
- This skill returns locators only. It does not download or upload. To keep a durable local copy (e.g. for an artifact or avatar), fetch the chosen URL yourself with the preflight below.
- Prefer an HTTPS
media_urlwith no credentials, query string, or fragment. Use any returned locator byte-for-byte; never rewrite its query string. - Preflight like a browser before fetching, one candidate at a time, bounded timeouts:
curl -fsSLI -A 'Mozilla/5.0' -H 'Accept: image/png,image/jpeg,image/gif,image/webp,image/*;q=0.5' -H 'Referer: <any-https-origin-that-is-not-the-image-host>' '<image-url>'
curl -fsSL --connect-timeout 10 --max-time 60 -A 'Mozilla/5.0' -H 'Accept: image/png,image/jpeg,image/gif,image/webp,image/*;q=0.5' -H 'Referer: <any-https-origin-that-is-not-the-image-host>' -o '<dest-file>' '<image-url>'
Accept only a final 2xx whose content type and file magic are an image. Reject hotlink-blocked, expiring, redirecting, 403/404, non-image, watermarked, or unstable URLs. Prefer PNG/JPEG; WEBP is fine except inside Word documents; convert HEIC to JPEG; avoid AVIF on web pages.
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.
- 8d ago First seen · 45 lines · 33 tokens per session scan A bdc736945744
image_search is a skill published in the GitHub repository 3338902669-ops/agent-orchestra (99 stars, last pushed 7d ago), licensed Apache-2.0. It adds 33 tokens to every session and 611 once invoked, about $0.0001 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 2026-10-08.
Other skills, from other repositories
security
Security scanning — injection detection, capability checks, audit trails.
status
System status and health checks — dashboard stats, agent health, worker status.
oh-my-dynamic
Multi-agent orchestration engine for complex tasks. Use when you need to break a complex query into subtasks, run them in parallel with a DAG engine, and synthesize results. Triggers on: multi-agent, parallel execution, orchestrate, DAG, decompose task, dynamic workflow.
evolve
Create, test, and improve functions at runtime — agents write their own code.
lifecycle
Session lifecycle management — transitions, state tracking, reactions.
memory
Persistent agent memory — store, recall, search across sessions.