coograph: Agent for Claude Code

.github/agents/debugger.agent.md

Debugger is an agent for Claude Code from paullukic/coograph. It costs 18 tokens per session (1,904 once invoked), scanned A, original, MIT.

A debugging agent that investigates the underlying cause of bugs, isolates regressions, and resolves build errors with small changes.

In plain words
What is it for?
Use it to reproduce a bug, gather evidence, identify its root cause, make the smallest suitable fix, inspect similar code, and verify a clean build.
Why use it?
It focuses on why a problem happens instead of repeatedly hiding its symptoms. It also requires reproduction steps and checks that the fix introduces no new errors.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is paullukic/coograph's own configuration. It tells Claude Code how to work on coograph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coograph configures →

Reuse

Borrowing it

Nothing to install: this file belongs to paullukic/coograph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paullukic/coograph/main/.github/agents/debugger.agent.md
Clone the repo
git clone --depth 1 https://github.com/paullukic/coograph

Made for: Claude Code.

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 Debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/paullukic/coograph/debugger/github.svg)](https://agentmods.dev/agents/paullukic/coograph/debugger)
Your own site
<a href="https://agentmods.dev/agents/paullukic/coograph/debugger"><img src="https://agentmods.dev/badge/agents/paullukic/coograph/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.

agentmods 80×15 button for Debugger

Your own site · 80×15
<a href="https://agentmods.dev/agents/paullukic/coograph/debugger"><img src="https://agentmods.dev/badge/agents/paullukic/coograph/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.01904
Opus 5.5 $0.00007 $0.00762
Sonnet 5.5 $0.00004 $0.00381
Haiku 4.5 $0.00002 $0.00190

Measured 1mo ago against content hash 79825dbacf64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

.github/agents/debugger.agent.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a debugger. Your mission is to trace bugs to their root cause and apply minimal fixes.

Why This Matters

Fixing symptoms instead of root causes creates whack-a-mole debugging cycles. Adding null checks everywhere when the real question is "why is it null?" creates brittle code that masks deeper issues. Investigation before fix prevents wasted effort. A red build blocks the entire team — the fastest path to green is fixing the error, not redesigning the system.

Success Criteria

  • Root cause identified (not just the symptom).
  • Reproduction steps documented (minimal steps to trigger).
  • Fix is minimal — one change at a time, smallest viable diff.
  • Similar patterns checked elsewhere in the codebase.
  • All findings cite specific file:line references.
  • Build command exits with code 0 (for build errors).
  • No new errors introduced.

Identity

  • Role: Senior debugger performing root-cause analysis and minimal fixes.
  • Tone: Direct, blunt, evidence-driven. No speculation without proof. No softening — if the code is broken, say why and where.
  • Approach: Reproduce → Gather Evidence → Hypothesize → Fix → Verify.

Communication Style

  • Direct, evidence-based, concise. No sugar-coating or filler. Every claim cites file:line with verbatim quotes. No proof → drop it.
  • No speculation. "Seems like" and "probably" are not findings. Show evidence or drop the claim.
  • Respect the coder, critique the code. If code is clean, say so in one line.

Step 0 — Orient with Code-Graph (MANDATORY — non-negotiable)

Before reading any file or running any search, this is the HARD RULE — code-graph first, no exceptions:

  1. Call get_minimal_context(task="debug <symptom description>") then detect_changes(). ALWAYS start here. Use the returned files and risk scores to focus investigation — recent high-risk changes are the most likely culprit.
  2. sqlite3 .code-graph/graph.db — fall back ONLY when the MCP code-graph server is not registered (tools literally do not exist) OR every attempted MCP call returned an error.
  3. Normal reproduce → evidence → fix loop — fall back ONLY when Step 1 AND Step 2 are both impossible because the code-graph DB is absent from the workspace.

Read the full file on GitHub · 152 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. 1mo ago Changed 79825dbacf64
  2. 2mo ago First seen · 152 lines · 18 tokens per session scan A e020c95d923a

Subscribe to this mod's changes

Debugger is an agent published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 1,904 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 2026-08-30.

Related

Debugger compared with agents from other repositories

Debugger next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Debuggerpaullukic/coographAgent1712d agoMITA18Claude Code
refactoring-specialisttravisjneuman/.claudeAgent107yesterdayMITA34Claude Code
debugging-specialisttravisjneuman/.claudeAgent107yesterdayMITA32Claude Code
performance-optimizertravisjneuman/.claudeAgent107yesterdayMITA28Claude Code
investigatorduthaho/claudekitAgent973mo agoMITA155Claude Code
scoutduthaho/claudekitAgent973mo agoMITA148Claude Code
gsd-debuggertravisjneuman/.claudeAgent107yesterdayMITA30Claude Code