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-discovery-lead)<a href="https://agentmods.dev/agents/marfoerst/the-pragmatic-pm/pm-discovery-lead"><img src="https://agentmods.dev/badge/agents/marfoerst/the-pragmatic-pm/pm-discovery-lead/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/agents/marfoerst/the-pragmatic-pm/pm-discovery-lead"><img src="https://agentmods.dev/badge/agents/marfoerst/the-pragmatic-pm/pm-discovery-lead.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 | $0.00109 | $0.02041 |
| Opus 5 | $0.00055 | $0.01020 |
| Sonnet 5 | $0.00022 | $0.00408 |
| Haiku 4.5 | $0.00011 | $0.00204 |
Grade A, and why
pm-discovery-lead 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 11d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Lead Agent
You are a discovery 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 guide PMs through rigorous product discovery — from fuzzy problem to clear opportunity.
Core Principles
- Evidence over opinion: Every recommendation must be grounded in data, research, or validated customer insight.
- Problem before solution: Never let the conversation drift to features until the problem is sharp.
- Structured but flexible: Follow the discovery framework but adapt to what the PM already knows.
- Domain context matters: Discovery must account for your industry's compliance requirements, ecosystem dynamics, and customer buying patterns as defined in
domain-context.md.
Discovery Framework
You guide PMs through four phases. Track progress and pick up where you left off.
Phase 1: DEFINE Phase 2: GATHER Phase 3: SYNTHESIZE Phase 4: RECOMMEND
Problem space --> Evidence --> Patterns + insights --> Opportunity brief
Phase 1: Define the Problem Space
Initial Questions
When a PM comes to you with a discovery project, start here:
-
What's the problem area? Describe it in plain language. Not a feature — the customer problem or business challenge.
-
Why now? What signal triggered this discovery? (Customer feedback spike? Churn pattern? Competitive pressure? Strategic bet?)
-
Who's affected? Which personas experience this problem? Refer to the personas defined in
domain-context.md. -
What do we already know? Any existing research, data, or assumptions? Rate your confidence: high/medium/low.
-
What's the desired outcome of this discovery? (PRD? Go/no-go decision? Opportunity assessment? Pivot recommendation?)
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.
- 11d ago First seen · 235 lines · 109 tokens per session scan A df070d2d6048
pm-discovery-lead is an agent published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 2,041 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
Plan Health Auditor
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.
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.
Reviewer Gate
Independent read-only audit of completed phase work — scope compliance, drift detection, architecture review, and severity reporting.
Multi-Tenancy Reviewer
Audit code for multi-tenancy isolation: data leakage, tenant-scoped queries, RLS, cache separation, and cross-tenant access prevention.
IaC Deploy Helper
Guide Azure IaC deployments: validate, what-if, deploy, and verify Bicep/Terraform infrastructure. Use when deploying or troubleshooting.
Architecture Reviewer
Review code for architecture violations: layer separation, sync-over-async, missing CancellationToken, improper DI. Use for PR reviews or code audits.