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 ai-analyst-lab/ai-analyst --skill analysis-designgit clone --depth 1 https://github.com/ai-analyst-lab/ai-analystWrote 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/ai-analyst-lab/ai-analyst/analysis-design)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/analysis-design"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/analysis-design/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/ai-analyst-lab/ai-analyst/analysis-design"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/analysis-design.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 | $0.00326 | $0.03255 |
| Opus 5.5 | $0.00130 | $0.01302 |
| Sonnet 5.5 | $0.00065 | $0.00651 |
| Haiku 4.5 | $0.00033 | $0.00326 |
Grade A, and why
analysis-design 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Analysis Design
Trigger: /analysis-design, "design an analysis for...", "I think X caused Y", "help me investigate..."
Type: Orchestrator — runs a multi-agent pipeline
Purpose
Takes a vague analytical hunch, stakeholder request, or business question and produces a rigorous, stakeholder-ready analysis plan through a multi-stage pipeline. Chains three specialized agents: Hypothesis Sharpener → Confound Scanner → (optional) Feedback Synthesizer.
This skill orchestrates the full lifecycle: hunch → testable hypothesis → threat assessment → investigation plan → V1 execution → feedback synthesis → V2 redesign.
When to Use
- A PM has a hunch but no plan: "I think removing the widget caused repeat purchases to drop"
- A vague request lands: "Can you look into why conversion dropped?"
- An analysis needs redesign after stakeholder feedback: "Here's V1 and the comments — help me build V2"
- Before starting any major investigation (prevents wasted work)
Inputs
| Input | Required | Source | Description |
|---|---|---|---|
{{HUNCH}} |
Yes | User | The vague hypothesis, business question, or analytical request |
{{DATA_PATH}} |
No | User or auto-detect | Path to relevant dataset(s). If not provided, uses active dataset from .knowledge/active.yaml |
{{AUDIENCE}} |
No | User | Who will consume the analysis (e.g., "VP of Product", "exec team", "cross-functional leads") |
{{V1_FINDINGS}} |
No | User or working/ | Path to V1 analysis output — triggers V2 redesign flow |
{{FEEDBACK}} |
No | User | Stakeholder feedback (comments, meeting transcript, Slack thread) — triggers Feedback Synthesizer |
{{URGENCY}} |
No | User | Timeline constraint (e.g., "need by EOD", "board meeting Friday"). Affects investigation depth. |
First action: architecture preview
Open by printing the preview below so the user sees the stages before Stage 1 runs.
Preview Format
If {{V1_FINDINGS}} or {{FEEDBACK}} is provided (V2 redesign scenario):
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 · 308 lines · 326 tokens per session scan A 6bfdd40d5ae5
analysis-design is a skill published in the GitHub repository ai-analyst-lab/ai-analyst (322 stars, last pushed 1mo ago), licensed MIT. It adds 326 tokens to every session and 3,255 once invoked, about $0.0013 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 2026-09-12.
analysis-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analysis-designai-analyst-lab/ai-analyst | Skill | 322 | 1mo ago | MIT | A | 326 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |