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.
git clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/commands/yuri-semenenko/ai-engineering-workspace/research)<a href="https://agentmods.dev/commands/yuri-semenenko/ai-engineering-workspace/research"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/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/commands/yuri-semenenko/ai-engineering-workspace/research"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/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 | $0.00019 | $0.00351 |
| Opus 5.5 | $0.00008 | $0.00140 |
| Sonnet 5.5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
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 6d 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.
What it actually says
Research Prompt
Role: Act as a senior engineer deciding a concrete technical question — comparing libraries, frameworks, APIs, or approaches — with evidence, not vibes.
Context: A choice needs to be made and defended, and the result will feed an RFC or ADR. This is the evidence step before the decision document, not the document itself.
Task: Produce a short research brief: a cited decision matrix, key findings, contradictions and gaps, and a recommendation that states its own confidence.
Constraints:
- Prefer primary sources (official docs, specs, changelogs, benchmarks, the source itself) over blog posts and SEO content. Read the repo's own constraints too.
- Cite every load-bearing claim; date volatile facts, since ecosystem claims rot.
- Separate what a source says from your inference.
- Surface contradictions explicitly; do not smooth them over. What you cannot resolve is an open question.
- Include a "do nothing / defer" option in the matrix.
- Bound the work to what the decision needs; this is not a literature review.
Output Format:
- Question and the criteria that matter (the matrix columns)
- Decision matrix: options as rows, criteria as columns, cells cited
- Key findings with citations
- Contradictions and gaps
- Recommendation, with confidence level and what would change it
- Handoff: which decision doc this feeds (RFC or ADR)
Success Criteria:
- Every cell and claim traces to a source.
- The recommendation states its uncertainty rather than overstating a thin base.
- A reader could take the matrix straight into an RFC or ADR.
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.
- 6d ago First seen · 37 lines · 19 tokens per session scan A 0204e6293ca5
research is a command published in the GitHub repository yuri-semenenko/ai-engineering-workspace (4 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 351 once invoked, about $0.0001 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 2026-10-31.
research compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| researchyuri-semenenko/ai-engineering-workspace | Command | 4 | 3d ago | MIT | A | 19 | GitHub Copilot |
| spec-trace-requirementsrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| ios-buildNagarjuna2997/ios-agent-skill | Command | 40 | 8d ago | MIT | A | 19 | Claude Code |
| sdd-setupGregorBiswanger/featherspec | Command | 70 | 1mo ago | MIT | A | 27 | Claude Code |
| playwright-executekatalon-labs/true-skills | Command | 10 | 17d ago | MIT | A | 117 | GitHub Copilot |
| test-maintenancekatalon-labs/true-skills | Command | 10 | 17d ago | MIT | A | 131 | GitHub Copilot |