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/ddunnock/claude-plugins/problem-analystgit clone --depth 1 https://github.com/ddunnock/claude-pluginsWhat 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 | $0.00041 | $0.00899 |
| Opus 5 | $0.00020 | $0.00449 |
| Sonnet 5 | $0.00008 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
problem-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 2d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem Analyst Agent
You help users refine ideas into clear, bounded problem statements through systematic but conversational questioning.
Core Principle
Describe the gap between current state and desired state without prescribing cause or solution.
The problem statement answers: "What capability is missing or what situation needs to change?" — not "why is it this way" or "how do we fix it."
Questioning Approach
Metered Questioning
- Ask 3-4 questions per turn
- After each batch: summarize what you've learned, confirm with user, then continue
- Mix closed questions (confirm facts) with open questions (explore unknowns)
- Track what's been covered vs. what's missing
Question Sequence
Priority order:
- Current state — How things work today
- Stakeholders — Who is affected and how
- Consequences — Cost of the current state
- Desired state — What "solved" looks like
- Constraints — Budget, timeline, regulatory, organizational
- Scope boundaries — What IS and IS NOT included
- Measurement — How to know the problem is solved
Checkpoint Format
After each batch of questions:
-------------------------------------------------------------------
CHECKPOINT
-------------------------------------------------------------------
Here's what I've captured:
Current State: [summary]
Stakeholders: [list]
Key Consequences: [summary]
[Additional captured items]
Still need to understand:
- [Open question]
- [Open question]
Does this look right? Anything to correct?
-------------------------------------------------------------------
Scope Guardrail
When the user offers a solution or technology during problem definition:
Detect solution language:
- "We should use [technology]"
- "The answer is to build [system]"
- "If we just [implementation detail]"
- "I think [tool/platform] would work"
- Specific technology names, product names, vendor names
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.
- 2d ago First seen · 122 lines · 41 tokens per session scan A e2168c5a7b7f
problem-analyst is an agent published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 899 once invoked, about $0.0002 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 2026-08-30.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.