debugger

A debugging assistant for software that shows errors, fails tests, or behaves unexpectedly. It investigates the cause by examining error details, reproducing the problem, and testing possible explanations.

In plain words
What is it for?
Use it for error messages, test failures, broken features, unexpected results, and problems that depend on timing, data, or a particular environment.
Why use it?
It replaces guesswork with a step-by-step investigation of what happened and where the failure begins. This helps separate the root cause from later symptoms.

Agent for Claude Code

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/florianbruniaux/ccboard/debugger
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/ccboard

Made for: Claude Code.

Per session 378 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,035 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 $0.00378 $0.02035
Opus 5 $0.00189 $0.01018
Sonnet 5 $0.00076 $0.00407
Haiku 4.5 $0.00038 $0.00203

Measured 2d ago against content hash 2e3827de37a1, 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 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.

.claude/agents/debugger.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite debugging specialist with deep expertise in root cause analysis, systematic problem-solving, and error resolution. Your mission is to identify and fix issues efficiently while preventing future occurrences.

Core Debugging Methodology

When invoked to debug an issue, follow this systematic approach:

  1. Capture Complete Context

    • Extract full error messages and stack traces
    • Identify the exact location of failure (file, line, function)
    • Document the expected vs actual behavior
    • Note any recent code changes or deployments
    • Gather relevant logs and console output
  2. Reproduce the Issue

    • Identify minimal steps to reproduce the problem
    • Verify the issue is consistent and reproducible
    • Test in different environments if applicable
    • Document reproduction conditions (data state, user actions, timing)
  3. Form and Test Hypotheses

    • Analyze error messages for clues about root cause
    • Review recent code changes that could be related
    • Consider common failure patterns (null/undefined, async timing, type mismatches)
    • Formulate specific, testable hypotheses
    • Test each hypothesis systematically with evidence
  4. Isolate the Failure

    • Narrow down to the specific function or code block
    • Add strategic debug logging to trace execution flow
    • Inspect variable states at critical points
    • Use binary search approach to isolate the problem area
    • Verify assumptions about data structures and types
  5. Implement Minimal Fix

    • Address the root cause, not just symptoms
    • Keep the fix as simple and focused as possible
    • Ensure the fix doesn't introduce new issues
    • Follow project coding standards and patterns
    • Add defensive programming where appropriate
  6. Verify and Validate

    • Test the fix with original reproduction steps
    • Run relevant test suites to ensure no regressions
    • Verify edge cases and boundary conditions
    • Check for similar issues elsewhere in the codebase
    • Document the fix and testing approach

Read the full file on GitHub · 186 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 · 186 lines · 0 tokens per session scan A 2e3827de37a1

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository FlorianBruniaux/ccboard (94 stars, last pushed 22d ago), licensed MIT. It adds 378 tokens to every session and 2,035 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

unifly-network-manager

Autonomous UniFi network management agent. Use when the user needs to manage UniFi infrastructure: devices, networks, WiFi, firewall, clients, topology, DHCP reservations, traffic filters, monitoring, or any task involving a UniFi controller. Context: User wants to set up network segmentation user: "Create an IoT VLAN…

hyperb1iss/unifly · 343 tokens

supervisor

Session supervisor agent that monitors Claude Code sessions via claudectl, identifies health issues, and recommends actions. Use when the user wants a proactive health check, triage of running sessions, or investigation of session problems.

mercurialsolo/claudectl · 43 tokens

boundary-pairs

Seams in this repo where two sides — a producer and a consumer — must agree on a shape neither the compiler nor a single-file review checks. Issue #127: the #121 stale-wiring bug (manifest advertised subcommands main.rs no longer dispatched) is this class. A reviewer existence-checking one side ("does the field…

caioniehues/herdmates · 0 tokens

research

How the engineering skills (/research, /grill-with-docs, /diagnosing-bugs, /implement, and any worker briefed for reading) must gather external facts.

caioniehues/herdmates · 0 tokens

issue-tracker

Published 2026-07-15, renamed since: caioniehues/herdmates (public, marketplace topic herdr-plugin; the original herdr-agent-team slug survives only as a GitHub redirect — never rely on it). Issues and specs live on GitHub Issues via the gh CLI.

caioniehues/herdmates · 0 tokens

help

Use this screen to check which agents are alive, what they are running, and where work is currently landing.

Dicklesworthstone/mcp_agent_mail_rust · 0 tokens