debug-assistant

debug-assistant is an agent for Claude Code from pyramidheadshark/claude-scaffold. It costs 21 tokens per session (809 once invoked), scanned A, original, MIT.

A debugging assistant that examines errors, tracebacks, failed tests, and unexpected behaviour to identify their likely root cause and a concrete fix.

In plain words
What is it for?
Use it for Python and type errors, failing tests, unexpected API responses, import problems, crashes, Docker build failures, Terraform errors, and dependency conflicts.
Why use it?
It replaces guesswork with a step-by-step diagnosis based on the error and the surrounding project context.

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/pyramidheadshark/claude-scaffold/debug-assistant
Clone the repo
git clone --depth 1 https://github.com/pyramidheadshark/claude-scaffold

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 debug-assistant

README.md
[![agentmods](https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/debug-assistant.svg)](https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/debug-assistant)
Your own site
<a href="https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/debug-assistant"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/debug-assistant.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 809 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 $0.00021 $0.00809
Opus 5 $0.00010 $0.00404
Sonnet 5 $0.00004 $0.00162
Haiku 4.5 $0.00002 $0.00081

Measured 3d ago against content hash 53fe0e7b111b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-assistant 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 3d 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/debug-assistant.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: debug-assistant

Purpose

Diagnoses errors, tracebacks, and unexpected behaviour systematically. Produces a root cause analysis and concrete fix, not just a guess.

When to Use

When encountering: Python tracebacks, failing tests, unexpected API responses, import errors, type errors, runtime crashes, Docker build failures, Terraform errors.

Diagnostic Workflow

Step 1: Classify the error

Category Signals First Actions
Import / module error ModuleNotFoundError, ImportError Check uv sync, check pyproject.toml
Type error mypy output, TypeError at runtime Read the type signature, check Pydantic model
Logic error Test fails but no exception Add intermediate print/log, check inputs
Async error RuntimeError: no running event loop Check asyncio_mode in pytest config
Docker error Build fails, container exits Read full docker logs, check entrypoint
Terraform error Plan/apply fails Read full error, check provider version, check .tfvars
Dependency conflict pip/uv resolver fails Check uv tree, check version constraints

Step 2: Gather context

uv run python -c "import {module}; print({module}.__version__)"
uv run pytest {failing_test} -xvs 2>&1 | tail -50
uv run mypy src/ --show-error-codes 2>&1 | head -30
docker logs {container} 2>&1 | tail -100

Step 3: Formulate hypothesis

State: "I believe the error is caused by X because Y." Never jump straight to a fix without a hypothesis.

Step 4: Verify before fixing

If possible, write a minimal reproduction:

# Minimal repro — paste this to verify the hypothesis

Step 5: Fix and verify

Apply the fix. Then run:

uv run pytest {failing_test} -xvs
uv run ruff check .
uv run mypy src/

All three must pass before the fix is complete.

Step 6: Document

Add to dev/status.md under "Known Issues and Solutions":

  • Problem description
  • Root cause
  • Solution applied

Read the full file on GitHub · 88 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. 3d ago First seen · 88 lines · 21 tokens per session scan A 53fe0e7b111b

Subscribe to this mod's changes

debug-assistant is an agent published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 809 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.

Related

Other agents, from other repositories

history-management

The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.

zeroclaw-labs/zeroclaw · 0 tokens

internals

This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.

zeroclaw-labs/zeroclaw · 0 tokens

mlops-engineer

ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.

pjt222/agent-almanac · 31 tokens

pr-fix

Analyze one or more failing CI jobs on a GitHub PR (using logs already collected) and fix them - edit sources, validate locally, commit and push. Use after pr-watch reports failures. Returns a request for the user when it cannot fix cleanly.

hardisgroupcom/sfdx-hardis · 56 tokens

api-designer

API design expert - REST/GraphQL consistency, documentation, versioning strategy.

fatihkan/badi · 19 tokens

requirements-reviewer

Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…

iroha924/mumei · 99 tokens