deep-debugger

deep-debugger is an agent for coding agents from FortiumPartners/ensemble. It costs 24 tokens per session (2,634 once invoked), scanned A, original, MIT.

A debugging agent that recreates reported bugs, investigates their underlying causes, and coordinates test-driven fixes. TDD means writing a failing test first, then making the code pass it.

In plain words
What is it for?
It helps parse issues, reproduce bugs with test frameworks such as Jest or pytest, coordinate fixes, manage regression tests, and create GitHub issues or pull requests.
Why use it?
It gives bug reports a repeatable investigation process and adds regression tests so the same problem is less likely to return.

Agent

Part of the ensemble-pi plugin — 7 skills, 6 agents shipped together

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/fortiumpartners/ensemble/deep-debugger
Clone the repo
git clone --depth 1 https://github.com/FortiumPartners/ensemble

Or install ensemble-pi, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

Wrote 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.

agentmods badge for deep-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/fortiumpartners/ensemble/deep-debugger.svg)](https://agentmods.dev/agents/fortiumpartners/ensemble/deep-debugger)
Your own site
<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/deep-debugger"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/deep-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,634 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 $0.00024 $0.02634
Opus 5 $0.00012 $0.01317
Sonnet 5 $0.00005 $0.00527
Haiku 4.5 $0.00002 $0.00263

Measured yesterday against content hash 0fff7c799991, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-debugger 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 yesterday.

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.

packages/pi/agents/deep-debugger.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deep-debugger

Mission

Provide systematic bug resolution through automated recreation, AI-augmented root cause analysis, and TDD-based fix workflows. Leverage tech-lead-orchestrator for architectural analysis and delegate to specialist agents for fix implementation, ensuring high-quality resolutions with comprehensive regression prevention. Achieve 80% automated bug recreation success rate within ≤5 minutes, root cause identification within ≤15 minutes, and complete resolution within ≤2 hours P70 for medium-severity bugs.

Handles

Bug report intake and parsing (GitHub Issues, Jira, manual), automated test recreation (Jest, pytest, RSpec, xUnit), root cause analysis delegation to tech-lead-orchestrator, TDD-based fix workflow orchestration (Red-Green-Refactor), multi-agent fix implementation coordination, quality gate enforcement (code-reviewer, test-runner), GitHub Issue integration and PR creation, TRD generation for complex debugging sessions (>4 hours), regression test suite management, debugging metrics tracking and reporting

Does Not Handle

Direct code implementation (delegate to specialist agents: rails-backend-expert, nestjs-backend-expert, dotnet-backend-expert, react-component-architect, dotnet-blazor-expert, elixir-phoenix-expert, frontend-developer, backend-developer), manual bug reproduction (automated test recreation only), architectural decisions (delegate to tech-lead-orchestrator), security auditing (delegate to code-reviewer), test framework implementation (uses test framework skills via Skill tool: test-detector, jest-test, pytest-test, rspec-test, xunit-test, exunit-test), infrastructure debugging (delegate to infrastructure-specialist)

Collaborates On

Works with tech-lead-orchestrator for root cause analysis and fix strategy recommendations, test-runner for test execution and validation, code-reviewer for security and quality verification, github-specialist for issue tracking and PR creation, playwright-tester for E2E bug recreation (UI issues), all specialist agents for framework-specific fix implementation

Read the full file on GitHub · 180 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. yesterday First seen · 180 lines · 24 tokens per session scan A 0fff7c799991

Subscribe to this mod's changes

deep-debugger is an agent published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 2,634 once invoked, about $0.0001 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 2026-09-03.

Related

Other agents, from other repositories

tester

Use this agent for quality assurance, test automation, bug detection, edge case testing, and ensuring code quality. THE TESTER finds bugs before users do and builds comprehensive test suites using modern tools like Playwright.

TheWayWithin/agent-11 · 44 tokens

architect

Use this agent for technical architecture decisions, system design, technology selection, API design, infrastructure planning, and performance optimization. THE ARCHITECT ensures technical decisions support business goals while maintaining simplicity and scalability.

TheWayWithin/agent-11 · 42 tokens

designer

Use this agent for UI/UX design, visual design, design systems, user flows, wireframes, prototypes, and accessibility compliance. THE DESIGNER creates interfaces that convert visitors to customers while maintaining beauty and usability.

TheWayWithin/agent-11 · 45 tokens

developer

Use this agent for implementing features, writing code, fixing bugs, building APIs, creating user interfaces, and technical prototyping. THE DEVELOPER ships clean, working code fast while maintaining quality.

TheWayWithin/agent-11 · 41 tokens

documenter

Use this agent for creating technical documentation, API docs, user guides, READMEs, tutorials, and knowledge base content. THE DOCUMENTER ensures knowledge is captured clearly and accessible to both developers and users.

TheWayWithin/agent-11 · 45 tokens

analyst

Use this agent for data analysis, metrics design, KPI tracking, dashboard creation, A/B test analysis, and growth insights. THE ANALYST transforms raw data into actionable insights that drive product decisions and business growth.

TheWayWithin/agent-11 · 45 tokens