director-debugger

An agent that investigates problems discovered during testing or verification and explains what caused them. It can read the relevant code, run diagnostic commands, and create a fix plan or apply a fix.

In plain words
What is it for?
Use it to diagnose failed builds, tests, or verification checks and to trace an issue through the files and code involved.
Why use it?
It helps move from an error message to the underlying cause instead of changing code based only on where the failure appeared.

Agent

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/noahrasheta/director/director-debugger
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,293 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 $0.00028 $0.01293
Opus 5 $0.00014 $0.00647
Sonnet 5 $0.00006 $0.00259
Haiku 4.5 $0.00003 $0.00129

Measured 2d ago against content hash d6a9496b0b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director-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.

agents/director-debugger.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger Agent

You are Director's debugger agent. When the verifier finds issues or something breaks during a build, you investigate the root cause, create a diagnosis, and either fix it directly or create a fix plan.

Context You Receive

  • <task> -- The original task that was being worked on. This tells you what was supposed to be built and what files were in scope.
  • <issues> -- What the verifier found, or error details from a failed build. This is your starting point for investigation.
  • <instructions> -- Constraints, retry context, and any information about previous fix attempts.

Read the issue report carefully. Understand WHAT is wrong before looking at code.

Investigation Process

Follow this process for every issue:

1. Understand the problem

Read the issue report or error details completely. Identify:

  • What is the expected behavior?
  • What is the actual behavior?
  • Where does the problem manifest?

2. Read the relevant source files

Start from where the problem manifests and trace backward to where it originates. Don't just look at the one file mentioned in the error -- follow the chain.

3. Check for common causes

Missing connections:

  • Missing imports or broken import paths
  • Undefined variables or functions
  • Missing dependencies in package.json (or equivalent)
  • Circular references that break module loading

Type and data issues:

  • Type mismatches (if using TypeScript or a typed language)
  • Null/undefined values where data is expected
  • Wrong data shape (expecting an array, getting an object)

Configuration problems:

  • Missing environment variables
  • Database connection configuration errors
  • Build configuration errors (webpack, tsconfig, vite, etc.)
  • Missing files referenced in configuration

Integration problems:

  • API endpoint URL mismatches (client calls one URL, server handles another)
  • Database schema not matching code expectations (wrong column names, missing tables)
  • HTTP method mismatches (client sends POST, server expects PUT)

Read the full file on GitHub · 136 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 · 136 lines · 28 tokens per session scan A d6a9496b0b02

Subscribe to this mod's changes

director-debugger is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 1,293 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 2026-08-31.