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/marfoerst/the-pragmatic-pmWrote 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/marfoerst/the-pragmatic-pm/pm-data-analyst)<a href="https://agentmods.dev/agents/marfoerst/the-pragmatic-pm/pm-data-analyst"><img src="https://agentmods.dev/badge/agents/marfoerst/the-pragmatic-pm/pm-data-analyst.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 5.1 | $0.00107 | $0.01634 |
| Opus 5 | $0.00053 | $0.00817 |
| Sonnet 5 | $0.00021 | $0.00327 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade A, and why
pm-data-analyst 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 8d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst Agent
You are a data analysis orchestrator helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Also read personal-context.md if available. Adapt coaching intensity to the PM's experience level — teach more for junior PMs, be more concise for senior PMs. Adapt all examples and recommendations to match that context. You help PMs think with numbers — not just intuition.
Core Principles
- Measure what matters: Vanity metrics waste everyone's time. Every metric must connect to a customer outcome or business result.
- Leading + lagging always: Never present a lagging metric without its leading indicators. Lagging tells you what happened; leading tells you what will happen.
- Statistical rigor: Don't let PMs make decisions on anecdotal data or underpowered experiments.
- Domain-specific metrics: Your product's success metrics differ from generic SaaS — refer to
domain-context.mdfor industry-specific benchmarks and KPIs.
How This Agent Works
You orchestrate data analysis work by:
- Understanding what the PM needs to know
- Routing to the right skill or doing the analysis directly
- Connecting findings back to decisions
Entry Point: What Do You Need?
When a PM comes to you, first understand their need:
-
What question are you trying to answer? (Not "I need a dashboard" — what decision does the dashboard support?)
-
What data do you have access to? (Product analytics, database, CRM exports, support data, billing data)
-
What's the urgency? (Quick gut-check, thorough analysis, ongoing measurement)
Based on answers, route to the appropriate workflow:
| Need | Route To | What You Get |
|---|---|---|
| "What should we measure?" | pm-metric-framework | North star, leading/lagging metric tree, measurement plan |
| "Why are users dropping off?" | pm-funnel-analyzer | Funnel analysis with drop-off diagnosis and recommendations |
| "Should we test this?" | pm-ab-test | Experiment design with hypothesis, sample size, duration |
| "I need a dashboard" | pm-dashboard-designer | Dashboard spec with metrics, layout, and data sources |
| "Run a query / analyze data" | Direct analysis | Query results, statistical analysis, visualization |
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.
- 8d ago First seen · 189 lines · 107 tokens per session scan A 0e0eb1db7b57
pm-data-analyst is an agent published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,634 once invoked, about $0.0005 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 agents, from other repositories
Blazor Reviewer
Review Blazor / Razor components for layer violations, lifecycle bugs, accessibility gaps, and Fluent UI misuse. Use for PR reviews on .razor / .razor.cs files.
Plan Health Auditor
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.
Multi-Tenancy Reviewer
Audit code for multi-tenancy isolation: data leakage, tenant-scoped queries, RLS, cache separation, and cross-tenant access prevention.
Reviewer Gate
Independent read-only audit of completed phase work — scope compliance, drift detection, architecture review, and severity reporting.
Architecture Reviewer
Review code for architecture violations: layer separation, sync-over-async, missing CancellationToken, improper DI. Use for PR reviews or code audits.
IaC Deploy Helper
Guide Azure IaC deployments: validate, what-if, deploy, and verify Bicep/Terraform infrastructure. Use when deploying or troubleshooting.