debug-agent

debug-agent is a skill for Claude Code, Codex from d-gangz/dgang-skills. It costs 142 tokens per session (2,733 once invoked), scanned A, original, MIT.

A session-review tool that investigates why an AI coding session produced a bad result or could have gone better. It separates problems in understanding, instructions, and execution.

In plain words
What is it for?
Use it to diagnose a specific failure or review a completed session, then apply file fixes only after you approve them.
Why use it?
It helps identify whether the issue came from missing context, unsuitable tools, flawed reasoning, or an unclear request before changing anything.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Good fit Use it to diagnose a specific failure or review a completed session, then apply file fixes only after you approve them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/d-gangz/dgang-skills/debug-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.

Any agent
npx skills add d-gangz/dgang-skills --skill debug-agent
Clone the repo
git clone --depth 1 https://github.com/d-gangz/dgang-skills

Made for: Claude Code, Codex.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/d-gangz/dgang-skills/debug-agent/github.svg)](https://agentmods.dev/skills/d-gangz/dgang-skills/debug-agent)
Your own site
<a href="https://agentmods.dev/skills/d-gangz/dgang-skills/debug-agent"><img src="https://agentmods.dev/badge/skills/d-gangz/dgang-skills/debug-agent/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 debug-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/d-gangz/dgang-skills/debug-agent"><img src="https://agentmods.dev/badge/skills/d-gangz/dgang-skills/debug-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,733 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 $0.00142 $0.02733
Opus 5 $0.00071 $0.01367
Sonnet 5 $0.00028 $0.00547
Haiku 4.5 $0.00014 $0.00273

Measured 10d ago against content hash 05779a1d628c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

debug-agent 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 10d 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.

skills/debug-agent/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Agent

Diagnose what went wrong in this session and apply the right fixes. Two invocation modes:

  • Failure-driven (typical) — user saw a specific bad output ("the dossier missed the qualification criteria"). Anchor on that symptom.
  • Generic review — user wants a retrospective ("how did this session go", "anything we could've done better"). No named failure; scan for the most prominent issues.

Two roles

This skill runs in one of two roles. Identify which one you are before doing anything else, then follow only that section.

  • §MAIN — you received /debug-agent (or an equivalent ask) from the user directly. You own user interaction and you apply any fixes. You do not diagnose inline — you spawn a fork to do that.
  • §FORK — you were spawned by a /debug-agent MAIN with a directive containing the phrase "diagnose only — return report, do not edit". You own the diagnosis and return a structured report. You never edit files.

If the directive that brought you here doesn't contain that phrase, you are MAIN.

Hard constraint (both roles)

Only diagnose the current session. Do not read other transcripts, session logs, or external traces. Evidence comes from this conversation's own history. (Forks inherit the conversation, so they have it natively.)


§MAIN — Workflow

You are the user-facing agent. Your job is small: dispatch the fork, present what it returns, and apply the fix only after explicit approval.

1. Fork yourself for diagnosis

Immediately spawn a fork via the Agent tool with no subagent_type (a fork inherits this conversation's context, which is the entire evidence base). Name it something like debug-diagnosis.

The fork's directive must:

  • Tell it to invoke this skill (/debug-agent) so it loads the §FORK instructions.
  • Contain the literal phrase "diagnose only — return report, do not edit" so it routes to §FORK.
  • Tell it to return a structured report (shape described in §FORK step 6).

Read the full file on GitHub · 210 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 210 lines · 142 tokens per session scan A 05779a1d628c

Subscribe to this mod's changes

debug-agent is a skill published in the GitHub repository d-gangz/dgang-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 2,733 once invoked, about $0.0007 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 skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens