app-debug-workflow

app-debug-workflow is a skill for Claude Code, Codex from MilkyWay008/Hermes-OTG. It costs 64 tokens per session (21,857 once invoked), scanned A, original, MIT.

A structured workflow for finding and fixing bugs in an unfamiliar full-stack codebase, meaning an application that includes both user-facing and server-side parts. It moves through discovery, verification, planning, fixing, and validation, with optional handoffs between sessions.

In plain words
What is it for?
Use it to audit an existing application for security, performance, reliability, or development-tooling issues, then organize and validate the fixes.
Why use it?
It gives debugging work a repeatable order when time is limited and the codebase is new to you. This reduces the risk of changing code before understanding or testing the problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md; mentions OpenCode.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/duck-research-wrapper.py --mode compare "Review this proposed fix document against the codebase...".

Good fit Use it to audit an existing application for security, performance, reliability, or development-tooling issues, then organize and validate the fixes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/MilkyWay008/Hermes-OTG
agentmods
npx agentmods add skills/milkyway008/hermes-otg/app-debug-workflow

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 app-debug-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/milkyway008/hermes-otg/app-debug-workflow.svg)](https://agentmods.dev/skills/milkyway008/hermes-otg/app-debug-workflow)
Your own site
<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/app-debug-workflow"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/app-debug-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 649
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 767
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 468
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00064 $0.21857
Opus 5 $0.00032 $0.10929
Sonnet 5 $0.00013 $0.04371
Haiku 4.5 $0.00006 $0.02186

Measured 8d ago against content hash 9c30fa28c56a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

app-debug-workflow scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If the server process exits immediately (exit code 1) without printing any server startup banner, the most likely cause is an import-time error in Python (e.g., `import nonexistent_module` deliberately placed in a route
data/skills/custom/app-debug-workflow/SKILL.md · 1,317 lines

How it starts

The opening of the file, as written. The whole thing — 1,317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Debug Workflow

Overview

This workflow is purpose-built for auditing an unfamiliar codebase under time pressure. It inverts the complex-project-workflow — instead of building from scratch, we start from an existing (buggy) codebase and work backward to find and fix issues.

Core loop: Discover → Duck-Verify → Plan → Handoff → Fix → Validate (iterate)

Multi-session architecture (optional — context health fallback):

  • Default (single session): Run Phases 0-6 in one session. Simpler, no handoff overhead.
  • Fallback (multi-session): If context health degrades (ECHO 🟡/🔴), split into Session A (debug/plan, Phases 0-4+6) and Session B (fix, Phase 5). Handoff docs in debug-fix-handoff/ make this seamless.
  • Why prepare for multi-session: The fix session (Phase 5) produces heavy tool call volume — reading files, editing, testing, repeating. Keeping this in the main session accelerates context degradation. The handoff exists to protect the primary session's context health.
  • Session A (Debug/Plan): Exploration, discovery, rubber-duck audit, task planning, handoff doc creation — NO code writing
  • Session B (Fix): Execute fixes from task registry via subagents/ACP — NO planning

Read the full file on GitHub · 1,317 lines

Files

What ships with it

3 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. 8d ago First seen · 1,317 lines · 64 tokens per session scan A 9c30fa28c56a

Subscribe to this mod's changes

app-debug-workflow is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 24d ago), licensed MIT. It adds 64 tokens to every session and 21,857 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

vicious-mockery

The bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report…

Hmbown/Wizards-of-the-Ghosts · 101 tokens

grill-with-docs

Cross-examine codebase architecture against official library documentation and API specs. Identifies deprecations, anti-patterns, and suboptimal library usage.

pedroiff0/awesome-skills · 36 tokens

engineering-incident-response-commander

An incident-response guide for managing production failures, coordinating responders, reviewing what happened afterward, and tracking service targets. SLOs and SLIs are measures used to define and monitor service reliability.

clowlove/Hermes-House · 58 tokens

hermes-s6-container-supervision

Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.

clowlove/Hermes-House · 43 tokens

hermes-telegram-setup

Set up and troubleshoot Telegram bot integration with Hermes Agent gateway — token config, pairing flow, gateway service management, and common pitfalls.

clowlove/Hermes-House · 33 tokens

coding-assistant

AI-powered coding assistant for code generation, explanation, debugging, and refactoring. Supports 50+ programming languages.

clowlove/Hermes-House · 27 tokens