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 opencmit/alphora --skill deep-researchgit clone --depth 1 https://github.com/opencmit/alphoraWrote 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/opencmit/alphora/deep-research)<a href="https://agentmods.dev/skills/opencmit/alphora/deep-research"><img src="https://agentmods.dev/badge/skills/opencmit/alphora/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/opencmit/alphora/deep-research"><img src="https://agentmods.dev/badge/skills/opencmit/alphora/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00159 | $0.02605 |
| Opus 5.5 | $0.00064 | $0.01042 |
| Sonnet 5.5 | $0.00032 | $0.00521 |
| Haiku 4.5 | $0.00016 | $0.00261 |
Grade A, and why
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 1mo 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements for Outputs
Final Report
Structure
- Title page: Topic, date, author line
- Executive summary: 3-5 sentence overview of key findings (written last)
- Table of contents: Auto-generated from headings
- Body sections: Logically organized with H2/H3 headings
- Conclusion & recommendations: Actionable takeaways
- References: Numbered list of all sources with URLs
Quality Standards
- Every factual claim MUST cite its source with
[n]notation linking to the references section - Charts and images MUST have captions explaining what they show
- Data tables MUST include units and time periods
- Minimum 3 distinct sources for any major conclusion
- No hallucinated statistics — every number must trace to collected evidence or computed code output
Visual Requirements
- Include at least one data-driven chart per major section (bar, line, pie, etc.)
- Reference images should be downloaded locally and embedded via relative paths
- All images saved under
/mnt/workspace/report/assets/ - Image references in markdown:
Formatting
- Use consistent heading hierarchy (H1 for title, H2 for sections, H3 for subsections)
- Use tables for structured comparisons
- Use blockquotes for key findings or direct quotes
- Number formatting: thousands separator for large numbers, 1 decimal for percentages
Intermediate Artifacts
All research materials MUST be persisted in the workspace so findings are not lost between iterations:
| Directory | Purpose |
|---|---|
/mnt/workspace/research/sources/ |
Extracted web page content (.txt files) |
/mnt/workspace/research/data/ |
Downloaded datasets and raw data |
/mnt/workspace/research/images/ |
Downloaded reference images |
/mnt/workspace/research/notes/ |
Research notes and outlines |
/mnt/workspace/report/ |
Final report markdown |
/mnt/workspace/report/assets/ |
Report images (charts + reference images) |
Sandbox Environment
What ships with it
5 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.
- 1mo ago First seen · 285 lines · 159 tokens per session scan A c53cb4f98d19
deep-research is a skill published in the GitHub repository opencmit/alphora (348 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 159 tokens to every session and 2,605 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
migrating-mastra-to-pydantic-ai
Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports @mastra/ or relies on Mastra agents, tools, workflows, memory, processors, streaming, approvals, skills, or subagents.
migrating-vercel-ai-sdk-and-eve-to-pydantic-ai
Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports ai, @ai-sdk/, or eve, or relies on generateText, streamText, ToolLoopAgent, useChat, Eve agents, tools, skills, subagents, approvals, sessions, channels, schedules…
migrating-openai-agents-sdk-to-pydantic-ai
Migrate Python OpenAI Agents SDK applications to Pydantic AI and, when warranted, Pydantic AI Harness. Use for agents.Agent, Runner, function tools, handoffs, guardrails, sessions, human approval, streaming, or SandboxAgent. Do not use for applications built directly on the OpenAI Responses API without the Agents SDK…
hep-upload
Publish an Agentlas package to Agent Cloud or the public Hub.
research-report
Research report on companies, competitors, markets or products: research a company, compare competitors, market landscape, funding, pricing, launches. Also to save a brief, summary or snapshot built from search results.
hephaestus-upload
Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.