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/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/deep-debugger)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/deep-debugger"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/deep-debugger/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/fortiumpartners/ensemble/deep-debugger"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/deep-debugger.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 | $0.00024 | $0.02634 |
| Opus 5.5 | $0.00010 | $0.01054 |
| Sonnet 5.5 | $0.00005 | $0.00527 |
| Haiku 4.5 | $0.00002 | $0.00263 |
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 1mo 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 — 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
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.
- 1mo ago First seen · 180 lines · 24 tokens per session scan A 0fff7c799991
deep-debugger is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 2,634 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
gsd-debug-session-manager
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
executor
Execute one task with TDD/self-review and return structured result.
test-writer
Drafts test files based on a feature spec and existing test patterns. Use to parallelize TDD — draft the next test while the lead implements the current step.
iloom-wave-verifier
Wave verification agent that checks must-have criteria from child issues after each swarm wave, invokes fix skills for failures, and reports structured results.\n\nExamples:\n \nContext: Orchestrator wants to verify that wave 1 work meets acceptance criteria\nuser: "Verify must-haves for issues #101, #102, #103 from…
builder
Implements a task using TDD — writes the test first, then the code, then refactors. The only agent with full access.
tdd-runner
Runs Kent Beck's red → green → refactor loop end-to-end for a single behavior change and returns one green-with-evidence verdict. Writes the failing test FIRST, runs it to confirm red, implements the minimum to go green, then refactors. Use when the user wants a behavior built/fixed test-first hands-off, or says "TDD…