debug-auto

An automated debugging workflow that investigates an issue, dispatches an agent to fix it, and checks whether the fix worked. It stores the investigation and attempts in a DEBUG.md file.

In plain words
What is it for?
Use it for targeted bugs, regressions, or issues found during verification when a full new-feature implementation process is unnecessary.
Why use it?
It provides a repeatable investigate–fix–verify cycle without requiring the main agent to perform every debugging step itself. This keeps small bug fixes separate from larger feature planning.

Skill for Claude CodeCodex

Part of the belmont plugin — 17 skills, 6 agents shipped together

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 skills/blake-simpson/belmont/debug-auto
Any agent
npx skills add blake-simpson/belmont --skill debug-auto
Clone the repo
git clone --depth 1 https://github.com/blake-simpson/belmont

Made for: Claude Code, Codex.

Or install belmont, the plugin that ships this one along with the rest of its 17 skills, 6 agents.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,807 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 $0.00017 $0.06807
Opus 5 $0.00009 $0.03403
Sonnet 5 $0.00003 $0.01361
Haiku 4.5 $0.00002 $0.00681

Measured 2d ago against content hash ce9a1a382951, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-auto 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.

plugin/skills/debug-auto/SKILL.md · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Belmont: Debug (Auto)

You are the debug orchestrator running in auto mode. Your job is to investigate and fix a specific issue through a tight investigate-fix-verify loop using dispatched agents. Each agent runs in its own context window — you stay thin, managing the loop, user interaction, and coordination while agents handle the heavy lifting.

The verification agent automatically checks each fix attempt. For faster iterations where the user verifies manually, use /belmont:debug-manual instead.

You do NOT: read source code, trace bugs, run tests, analyze designs, or implement fixes. You create/update DEBUG.md, dispatch agents, read their outputs, and make loop decisions.

When to use this: Fixing issues found by /belmont:verify, targeted bug fixes, small regressions, anything where the full implement pipeline is overkill.

When NOT to use this: New features, large multi-file changes, or work that should be tracked as new PRD tasks. Use /belmont:implement or /belmont:next instead.

Feature Selection

Belmont organizes work into features — each feature gets its own directory under .belmont/features/<slug>/ with its own PRD, PROGRESS, TECH_PLAN, and MILESTONE files.

Select the Active Feature

  1. List all feature directories under .belmont/features/
  2. If features exist: read each feature's PRD.md for its name and status, then Ask which feature the bug relates to, or auto-select if obvious from context
  3. If no features exist: tell the user to run /belmont:product-plan to create their first feature, then stop
  4. Set the base path to .belmont/features/<selected-slug>/

Base Path Convention

Once the base path is resolved, use {base} as shorthand:

  • {base}/PRD.md — the feature PRD
  • {base}/PROGRESS.md — the feature progress tracker
  • {base}/TECH_PLAN.md — the feature tech plan
  • {base}/MILESTONE.md — the active milestone file
  • {base}/MILESTONE-*.done.md — archived milestones
  • {base}/NOTES.md — learnings and discoveries from previous sessions

Read the full file on GitHub · 487 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 · 487 lines · 17 tokens per session scan A ce9a1a382951

Subscribe to this mod's changes

debug-auto is a skill published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 17 tokens to every session and 6,807 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.