A command for investigating bugs whose apparent symptom may have a different underlying cause, such as intermittent failures or race conditions.

It is for exploring likely root causes, comparing them with similar cases, suggesting debugging steps, and reporting supporting or contradictory evidence.

It helps when a stack trace or simple file inspection cannot identify the real source of the problem.

neo-debug — Command for coding agents by Parslee-ai: A command for investigating bugs whose apparent symptom may…

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 commands/parslee-ai/neo/neo-debug

Clone the repo

git clone --depth 1 https://github.com/Parslee-ai/neo

Or install neo, the plugin that ships this one along with the rest of its 9 skills, 18 commands, 1 agent, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/parslee-ai/neo/neo-debug.svg)](https://agentmods.dev/commands/parslee-ai/neo/neo-debug)

Your own site

<a href="https://agentmods.dev/commands/parslee-ai/neo/neo-debug"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/neo-debug.svg" alt="Measured on agentmods" height="20"></a>

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 415 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 5.1	$0.00056	$0.00415
Opus 5	$0.00028	$0.00208
Sonnet 5	$0.00011	$0.00083
Haiku 4.5	$0.00006	$0.00042

Measured 5d ago against content hash b36be7b567c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

neo-debug 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 5d 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.

commands/neo-debug.md · 62 lines

What it actually says

Get debugging assistance from Neo.

Usage

/neo-debug <error message or bug description>

Description

Use this command when debugging complex issues, especially intermittent bugs or race conditions. Neo uses semantic pattern matching to identify likely root causes.

Examples

/neo-debug TypeError in data processing pipeline

/neo-debug Race condition in concurrent task processor

/neo-debug Memory leak happening after 1000+ requests

What Happens

Neo will:

Analyze the error or bug description
Identify likely root causes using semantic patterns
Search memory for similar debugging scenarios
Suggest debugging strategies and fixes with confidence scores

Presentation

Invoke with --json and follow the agent's communication protocol (agents/neo.md). For debugging specifically:

Lead with orchestrator.summary, then the leading hypothesis.
Report what was ruled out, not just what was concluded. Every hypothesis_rejected event and every simulation issue in risk_found narrows the search for the user — that is the substance of a debugging session.
Say what evidence supports the leading hypothesis and what would falsify it.
If memory_found fired, say so: a prior occurrence of this failure is the single most useful thing Neo can contribute.
Never present a hypothesis as a diagnosis. Neo does not run the code.

Parameters

This command uses read-only advise mode. It does not apply fixes, execute commands, or update durable memory.

<description> - Error message or bug description (required)

Include: error messages, frequency, reproduction steps, environment details

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.

5d ago First seen · 62 lines · 56 tokens per session scan A b36be7b567c1

Subscribe to this mod's changes

neo-debug is a command published in the GitHub repository Parslee-ai/neo (16 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 415 once invoked, about $0.0003 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.

Debugging

neo-debug

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Usage

Description

Examples

What Happens

Presentation

Parameters

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement