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 SearchCans/searchcans-skills --skill searchcans-deep-researchgit clone --depth 1 https://github.com/SearchCans/searchcans-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/searchcans/searchcans-skills/searchcans-deep-research)<a href="https://agentmods.dev/skills/searchcans/searchcans-skills/searchcans-deep-research"><img src="https://agentmods.dev/badge/skills/searchcans/searchcans-skills/searchcans-deep-research/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/searchcans/searchcans-skills/searchcans-deep-research"><img src="https://agentmods.dev/badge/skills/searchcans/searchcans-skills/searchcans-deep-research.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 | $0.00089 | $0.00946 |
| Opus 5 | $0.00044 | $0.00473 |
| Sonnet 5 | $0.00018 | $0.00189 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
searchcans-deep-research 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SearchCans Deep Research
Investigate a defined question with current localized web sources. Build an evidence bundle with an explicit source budget before writing conclusions; do not treat search snippets as proof.
Set the scope
Collect the research question, decision it supports, geographic and language scope, freshness requirement, exclusions, and source budget. If a missing constraint would materially change the answer, ask one concise question before searching.
Write 3–5 distinct subquestions before calling the API. Cover the main claim, alternatives, primary evidence, material objections, and decision implications. The subquestions are the auditable research plan; do not start broad searching without them.
Set SEARCHCANS_API_KEY in the execution environment. Never put a key in a prompt, file, command output, or report.
Build the evidence bundle
Pass the 3–5 subquestions to the script. Add --query only for an additional search formulation that the plan requires. Keep the source budget small unless the user explicitly needs broader coverage.
python scripts/deep_research.py "What is changing in the EU AI Act for SaaS teams?" \
--subquestion "What official EU AI Act milestones apply to SaaS teams?" \
--subquestion "Which obligations differ for providers and deployers?" \
--subquestion "What 2026 guidance changes implementation priorities?" \
--country eu --language en --max-sources 5 --out research-bundle.json
Use --headless only when an important source requires JavaScript rendering. Start with --proxy 0; escalate one tier only after an empty or blocked result. Use --max-sources as a strict extraction budget.
Before research, the default --account-mode auto makes one Account API pre-flight call. It estimates search and Reader costs, stops if the planned searches cannot fit, and otherwise reduces max-sources to a safe Reader budget. It also sets --max-concurrency auto to the account's Parallel Lane count, so simultaneous searches and reads never exceed that observed limit. Use warn to retain scope while recording a warning, enforce to stop instead of reducing scope, cap to require budget capping, or off to disable account-aware controls. Do not treat a capped run with zero extracted sources as evidence for consequential claims.
What ships with it
4 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 · 65 lines · 89 tokens per session scan A 9d9c731bdff5
searchcans-deep-research is a skill published in the GitHub repository SearchCans/searchcans-skills (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 89 tokens to every session and 946 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.