debug

debug is a skill for Claude Code, Codex from GCWing/BitFun. It costs 28 tokens per session (861 once invoked), scanned B, original, MIT.

An evidence-driven workflow for finding runtime bugs by testing hypotheses with focused logs and reproduction steps. Runtime means while a program is running, rather than while it is being built.

In plain words
What is it for?
Use it to add targeted instrumentation, collect reproduction data, inspect filtered logs, confirm a cause, and then apply and clean up a fix.
Why use it?
It prevents speculative fixes by requiring observable evidence and confirmation of the root cause first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add targeted instrumentation, collect reproduction data, inspect filtered logs, confirm a cause, and then apply and clean up a fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gcwing/bitfun/debug
About the project

BitFun is a desktop AI agent that turns tasks into interactive mini-apps while also writing code, creating documents, and controlling computers. It is for software development and general desktop work across Windows, macOS, and Linux. Its catalogue entries extend the agent with skills, agents, and instructions.

GCWing/BitFun · 2,077 stars · on GitHub

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 GCWing/BitFun --skill debug
Clone the repo
git clone --depth 1 https://github.com/GCWing/BitFun

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/gcwing/bitfun/debug.svg)](https://agentmods.dev/skills/gcwing/bitfun/debug)
Your own site
<a href="https://agentmods.dev/skills/gcwing/bitfun/debug"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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: 2 findings, up to medium

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 →

  • medium Data Exfiltration · line 84
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Server-Side Request Forgery · line 84
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
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 $0.00028 $0.00861
Opus 5 $0.00014 $0.00430
Sonnet 5 $0.00006 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured yesterday against content hash d5f8b13fe94f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

debug scanned grade B 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/debug-log-server.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

void fetch('http://127.0.0.1:7469/log', { method: 'POST',
src/crates/assembly/core/builtin_skills/debug/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence-driven debugging

Evidence-driven debugging mode activated. Follow the workflow below:

  1. Generate multiple hypotheses based on the problem described by the user.

  2. Insert narrow, hypothesis-specific instrumentation for each hypothesis.

  3. Provide reproduction steps and ask the user to reproduce the issue.

  4. Read the captured runtime data and identify the confirmed root cause.

  5. Implement fix based on the confirmed root cause.

  6. If the user confirms the issue has been resolved, clean up all inserted log statements; otherwise, add more logs or generate new hypotheses

IMPORTANT: Do not implement a fix until it is supported by runtime evidence. IMPORTANT: Do not clean up instrumentation until the user confirms the issue has been fixed.

Rules

  • Before reading debug-agent.log, check its size and approximate entry count. Do not read a large log end-to-end in one pass; filter by hypothesis ID, location, time range, or other relevant keywords, and write a small analysis script when aggregation or correlation is needed.

  • Before each new request for the user to reproduce the issue, clear the existing debug-agent.log so that the next capture is attributable to that reproduction. If the historical entries may be needed, create a separate backup first (for example, with a timestamp or reproduction-batch suffix), then clear the active log.

  • Separate diagnosis from repair selection. Assess whether the confirmed cause calls for a root-cause fix, a smaller mitigation, or both. A mitigation that merely masks the symptom must not be presented as the root-cause fix.

  • If there are multiple viable fixes, or the root-cause fix has a materially larger change surface, present the options, trade-offs, and verification implications to the user and ask them to choose before editing production code. If one proportionate root-cause fix is clearly preferred, explain why and proceed only after the runtime evidence supports it.

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file 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. yesterday First seen · 102 lines · 28 tokens per session scan B d5f8b13fe94f

Subscribe to this mod's changes

debug is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 861 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Related

Other skills, from other repositories

memstack-development-performance-audit

Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.

cwinvestments/memstack · 69 tokens

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.

sickn33/agentic-awesome-skills · 34 tokens

task-management

Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID…

agentscope-ai/AgentTeams · 89 tokens

task-coordination

Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.

agentscope-ai/AgentTeams · 36 tokens

mcporter

Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.

agentscope-ai/AgentTeams · 47 tokens

project-management

Use when admin asks to start a multi-worker project, when a Worker @mentions you with task completion in a project room, when project plan changes are needed, or when a blocked task needs resolution.

agentscope-ai/AgentTeams · 43 tokens