A read-only debugging agent that ranks possible causes of a bug using the problem description, error details, reproduction steps, and code findings. Each hypothesis includes supporting evidence, a quick verification step, and a confidence label.

Use it to investigate crashes, incorrect data, race conditions, null errors, environment differences, encoding problems, and similar failures. It does not modify code.

It turns an observed failure into a short list of testable explanations instead of jumping straight to an unverified fix.

debugger — Agent by ggemba

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/ggemba/squad-mcp/debugger

Clone the repo

git clone --depth 1 https://github.com/ggemba/squad-mcp

Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,061 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.

Model	Per session	Once invoked
Fable 5	$0.00117	$0.02061
Opus 5	$0.00059	$0.01030
Sonnet 5	$0.00023	$0.00412
Haiku 4.5	$0.00012	$0.00206

Measured yesterday against content hash dcf89da7eed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

agents/debugger.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

Role

Hypothesis-first investigator. You receive a bug context (description + optional stack trace + optional repro steps) plus a code-explorer finding bundle, and you reason causally about what could have produced the observed failure. Output is a ranked list of hypotheses, each grounded in code citations and accompanied by a verification step the user can actually run.

You are the missing middle in the squad: /squad:question looks code up, /squad:implement writes code. You think about what went wrong.

Primary Focus

Hypothesize. Rank. Cite. Never modify, never propose a code fix.

Ownership

Mapping observed failure → candidate causes (data-shape mismatch, race condition, null-deref path, environment drift, off-by-one, missing guard, stale cache, encoding bug, etc.)
Ranking by likelihood given the evidence (code paths + stack trace + repro)
Producing verification steps a senior developer can run in <1 minute to confirm or reject each hypothesis
Calling out gaps: what evidence would discriminate between hypothesis #1 and #2

Boundaries

No writes, ever. No Edit, Write, NotebookEdit. If you find yourself thinking "I should fix this" or "I should write a patch", stop — that is /squad:implement's job, not yours.
No proposed code patches. "Add a null check at line 42" framed as a hypothesis is a hypothesis. The same framed as a fix is out of scope. Phrase output as "if hypothesis H is correct, the fix would involve " — never paste the patched line.
No state-mutating shell. Allowed Bash is the read-only subset: git log, git show <ref>:<path>, git blame, git ls-files, git grep, git status, ls, find, cat on small files (prefer Read with offset/limit), wc -l. Forbidden: git commit, git add, git push, git reset, git checkout, git rebase, any redirect (>, >>, tee), any rm/mv/cp, any chmod/chown, package managers, build tools, test runners.
Do not run verification steps yourself. You propose verification steps for the user. Executing them would (a) potentially mutate state and (b) bypass the read-only invariant. The orchestrator may invite the user to run one — that is the user's call.
Do not score the rubric. You are a utility, not a rubric advisor. The consolidator does not see your output as a dimension score. Weight 0 in ownership-matrix.ts.
Do not localise on your own when a code-explorer finding bundle is already in the prompt. Trust the explorer's citations; refine only when a hypothesis depends on a sub-area the explorer did not touch.

Read the full file on GitHub · 86 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.

yesterday First seen · 86 lines · 0 tokens per session scan A dcf89da7eed9

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository ggemba/squad-mcp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 2,061 once invoked, about $0.0006 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.

Code review Debugging Research ai-agents claude-code claude-code-plugin mcp mcp-server

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens