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 agentmods add agents/ai-analyst-lab/ai-analyst/indexgit 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/agents/ai-analyst-lab/ai-analyst/index)<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst/index"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst/index.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00959 |
| Opus 5 | $0.00000 | $0.00479 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
INDEX 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 5d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Index
System Variables (auto-resolved)
| Variable | Value | Used in |
|---|---|---|
{{DATE}} |
Current date, YYYY-MM-DD | All agent output filenames |
{{DATASET_NAME}} |
Short name derived from data path or user input | File naming, report headers |
{{BUSINESS_CONTEXT_TITLE}} |
Short title derived from {{BUSINESS_CONTEXT}} |
Question brief header |
{{RUN_ID}} |
Unique run identifier (YYYY-MM-DD_question-slug) | Run Pipeline, Resume Pipeline |
{{RUN_DIR}} |
Per-run output directory path | All agents during pipeline |
{{SQL_PATTERNS}} |
Archaeology-retrieved SQL patterns | Analysis agents |
{{CORRECTIONS}} |
Logged corrections for current context | Analysis agents |
{{LEARNINGS}} |
Category-specific learnings | Question Framing, Storytelling |
{{ENTITY_INDEX}} |
Disambiguation index | Question Router |
{{ORG_CONTEXT}} |
Business context (glossary, products, teams) | Question Framing, Storytelling |
{{THEME}} |
Active theme name | Chart Maker, Deck Creator |
{{CONTEXT}} |
Presentation context (workshop/talk/analysis) | Story Architect, Deck Creator |
{{STORYBOARD}} |
Story Architect output | Chart Maker, Storytelling |
{{FIX_REPORT}} |
Visual Design Critic feedback | Chart Maker (fix pass) |
{{DECK_FILE}} |
Generated deck path | Visual Design Critic |
{{CONFIDENCE_GRADE}} |
Validation confidence score (A-F) | Storytelling, Deck Creator |
Agents
| Agent | Path | Invoke When |
|---|---|---|
| Question Framing | agents/question-framing.md |
User provides a business problem to analyze |
| Hypothesis | agents/hypothesis.md |
Questions are framed, need testable hypotheses |
| Data Explorer | agents/data-explorer.md |
Need to understand what data exists in a source |
| Descriptive Analytics | agents/descriptive-analytics.md |
Need to analyze a dataset (segmentation, funnels, drivers) |
| Overtime / Trend | agents/overtime-trend.md |
Need time-series analysis or trend identification |
| Cohort Analysis | agents/cohort-analysis.md |
Need cohort retention curves, LTV analysis, or vintage comparison |
| Root Cause Investigator | agents/root-cause-investigator.md |
Initial analysis found an anomaly — need to drill down iteratively to find the specific root cause |
| Opportunity Sizer | agents/opportunity-sizer.md |
Root cause identified or opportunity found — quantify the business impact with sensitivity analysis |
| Experiment Designer | agents/experiment-designer.md |
Need to test a causal hypothesis — designs A/B tests or quasi-experimental analyses with power estimation and decision rules |
| Story Architect | agents/story-architect.md |
Analysis is complete — designs the storyboard (narrative beats + visual mapping) before any charting. Pass {{CONTEXT}} for workshop/talk closing sequences. |
| Chart Maker | agents/chart-maker.md |
Need to generate a specific chart. |
| Visual Design Critic | agents/visual-design-critic.md |
After Chart Maker generates charts — reviews against SWD checklist. After Deck Creator — reviews slide-level design with {{DECK_FILE}} and {{THEME}}. |
| Narrative Coherence Reviewer | agents/narrative-coherence-reviewer.md |
After Story Architect produces the storyboard, before charting — reviews story flow, beat structure, and Closing beats if present |
| Storytelling | agents/storytelling.md |
Analysis and charts are complete, need a narrative |
| Source Tie-Out | agents/source-tieout.md |
After Data Explorer, before analysis — verify data loading integrity by comparing pandas direct-read vs DuckDB SQL on foundational metrics. HALT on mismatch. |
| Validation | agents/validation.md |
Need to verify findings before presenting |
| Deck Creator | agents/deck-creator.md |
Need to create a presentation from analysis. Supports {{THEME}} (analytics-dark) and {{CONTEXT}} (workshop/talk closing sequence). |
| Comms Drafter | agents/comms-drafter.md |
Need stakeholder communications (Slack summary, email brief, exec summary). Non-critical — pipeline continues if this fails. |
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.
- 5d ago First seen · 44 lines · 0 tokens per session scan A daad16669c50
INDEX is an agent published in the GitHub repository ai-analyst-lab/ai-analyst (297 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 959 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.