debug

An autonomous debugger for the Microbot client and engine, including its pathfinder, walker, widgets, cache layer, and agent server. It reproduces a reported bug, changes the engine code, rebuilds the client, and checks the result.

In plain words
What is it for?
Use it for bugs in Microbot's own client or engine, rather than scripts written by users.
Why use it?
It takes the investigation from a bug report to a tested code change while stopping when the problem cannot be reproduced or repeated fixes fail.

Skill for Claude CodeCodex

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/chsami/microbot/debug
Any agent
npx skills add chsami/Microbot --skill debug
Clone the repo
git clone --depth 1 https://github.com/chsami/Microbot

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00100 $0.03368
Opus 5 $0.00050 $0.01684
Sonnet 5 $0.00020 $0.00674
Haiku 4.5 $0.00010 $0.00337

Measured 2d ago against content hash 2044dac1915e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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 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.

Makes network callslowCapability

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

A **Sonnet 4.6 subagent** owns the mechanical CLI/HTTP work: starting the client, logging in, deploying probes, rebuilding, restarting, and collecting raw outputs. This keeps your context clean (gradle/curl/log noise sta
.claude/skills/debug/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microbot Engine Debugger

You are an autonomous debugger for the Microbot client/engine itself — not user-authored scripts. You will be given a free-text bug description and are expected to reproduce, root-cause, patch, and verify the fix without further input.

Inputs

  • A free-text description of the bug (the entire /debug argument string).
  • The current working tree. Treat any uncommitted changes as in-progress engine work that may be related.

Outputs

  • Engine source edits, left uncommitted for the user to review.
  • A final detailed explanation in chat: what was broken, how you reproduced it, what you changed, how you verified it. The user said they want to read this, so do not skip it.

Stopping conditions

  • Success: fix is applied, client rebuilt and restarted, probe confirms the bug is gone, and no existing behavior regressed. Stop and report.
  • Budget: up to 5 patch attempts. On the 5th failed attempt, stop and report what you tried, what you learned, and what you'd try next.
  • Dead-end: if you cannot even reproduce the bug after 3 probes, stop and report — don't guess at fixes without a repro.

Model split: Opus drives, Sonnet executes

You (Opus 4.7) own all the thinking — orientation, root-cause analysis, probe design, patch writing, verification interpretation, and the final report. Do not delegate understanding.

A Sonnet 4.6 subagent owns the mechanical CLI/HTTP work: starting the client, logging in, deploying probes, rebuilding, restarting, and collecting raw outputs. This keeps your context clean (gradle/curl/log noise stays in the subagent) and is faster + cheaper for mechanical command runs.

Spawn the subagent with the Agent tool, passing model: "sonnet" and subagent_type: "general-purpose". Brief it like a teammate: tell it exactly which commands to run and what to return. Always cap response length and ask for raw outputs (log tails, status codes, JSON bodies) rather than the subagent's interpretation — you do the interpreting.

Read the full file on GitHub · 230 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 · 230 lines · 100 tokens per session scan A 2044dac1915e

Subscribe to this mod's changes

debug is a skill published in the GitHub repository chsami/Microbot (205 stars, last pushed 3d ago), licensed BSD-2-Clause. It adds 100 tokens to every session and 3,368 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens