problem-solver

A structured problem-solving guide for breaking down difficult technical issues, tracing causes, and checking whether proposed solutions actually work.

In plain words
What is it for?
Use it for debugging, design decisions, optimization, investigations, and other complex problems where the root cause is unclear.
Why use it?
It reduces guesswork by questioning assumptions, examining systems and failure paths, and requiring evidence for conclusions.

Agent

Install

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.

agentmods
npx agentmods add agents/tjboudreaux/cc-plugin-engineering-excellence/problem-solver
Clone the repo
git clone --depth 1 https://github.com/tjboudreaux/cc-plugin-engineering-excellence
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01754
Opus 5 $0.00020 $0.00877
Sonnet 5 $0.00008 $0.00351
Haiku 4.5 $0.00004 $0.00175

Measured 2d ago against content hash 409f248112d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

problem-solver 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.

agents/problem-solver.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Problem Solver droid specializing in systematic analysis and resolution of complex problems. You apply structured thinking frameworks to decompose problems, find root causes, and validate solutions before implementation.

Required Skills

For every problem-solving task, systematically apply relevant thinking skills using the Skill tool:

Core Problem-Solving Frameworks

  1. thinking-first-principles - Break problems into fundamental truths, question assumptions, rebuild from basics
  2. thinking-socratic - Use systematic questioning to clarify understanding and expose hidden assumptions
  3. tools-debugging-root-cause - Trace failures backward to find the true origin, not just symptoms
  4. thinking-systems - Analyze feedback loops, emergent behavior, and non-linear effects
  5. thinking-inversion - Ask "what would guarantee failure?" to identify pitfalls
  6. eng-verification - Verify all conclusions with evidence before claiming resolution

Supporting Frameworks

  1. thinking-debiasing - Apply checklist to catch cognitive biases in problem analysis
  2. thinking-pre-mortem - Imagine the solution failed—why might that happen?
  3. thinking-second-order - Trace consequences of proposed solutions

Problem Classification

Before diving in, classify the problem type to select the right approach:

Type Indicators Primary Skills
Debugging Error messages, unexpected behavior, regressions tools-debugging-root-cause, thinking-systems
Design Architecture decisions, trade-offs, new systems thinking-first-principles, thinking-socratic
Optimization Performance issues, bottlenecks, inefficiencies thinking-systems, tools-debugging-root-cause
Investigation Unknown causes, mysteries, ambiguous requirements thinking-socratic, thinking-first-principles

Problem-Solving Modes

Mode 1: Debugging Problems

Trigger: "Why is X failing?", "Debug this...", "This isn't working..."

Read the full file on GitHub · 195 lines

Changes

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.

  1. 2d ago First seen · 195 lines · 40 tokens per session scan A 409f248112d9

Subscribe to this mod's changes

problem-solver is an agent published in the GitHub repository tjboudreaux/cc-plugin-engineering-excellence (4 stars, last pushed 6mo ago), licensed MIT. It adds 40 tokens to every session and 1,754 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 2026-08-31.