using-disbug

Guidelines for using Disbug, a bug-reporting and session-recording tool, as evidence when investigating software problems.

In plain words
What is it for?
Use it to inspect Disbug reports, sessions, pins, or downloaded report data while reproducing, diagnosing, fixing, and verifying bugs.
Why use it?
They help establish what the user expected, what happened, and which logs, network activity, screenshots, or other evidence are relevant instead of guessing from a report.

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/disbug-io/disbug-cli/using-disbug
Any agent
npx skills add disbug-io/disbug-cli --skill using-disbug
Clone the repo
git clone --depth 1 https://github.com/disbug-io/disbug-cli

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 638 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 $0.00023 $0.00638
Opus 5 $0.00012 $0.00319
Sonnet 5 $0.00005 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured yesterday against content hash f16ce5c13140, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-disbug 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 yesterday.

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.

internal/configure/assets/using-disbug/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Disbug

Use Disbug as evidence for reproducing, diagnosing, fixing, and verifying a reported bug.

Choose the available interface

  • If you can run shell commands and disbug is installed, use the CLI. Run disbug --help or disbug <command> --help when you need exact syntax.
  • If you have Disbug MCP tools but no shell access, use those tools. Read their schemas for exact inputs.
  • Follow the user's requested interface when they name one.

Do not assume that having the disbug mcp command means the current agent is connected to it. If MCP tools are unavailable, use the CLI when possible or ask the user to run disbug configure and restart the agent.

Investigation workflow

  1. Treat the report URL as the stable identity for a cloud report. Preserve any ?pin= selection.
  2. Start with the session summary or the selected pin's feedback. Establish what the user expected, what happened, the page, and the relevant time window.
  3. Fetch only the evidence needed for the current hypothesis. Useful evidence can include console output, network activity, user actions, page state, screenshots, storage, system context, and files attached to a pin. Session and pin output includes attachment filenames and IDs; download a relevant attachment so its contents reach the agent.
  4. Correlate evidence before changing code. Prefer timestamps, request IDs, routes, and visible state over guesses.
  5. Implement the smallest well-supported fix, then run the repository's relevant checks.
  6. Verify against the original report. If new reports are arriving during a live debugging session, use Disbug's watch capability to continue from fresh evidence.
  7. When a user-requested fix is verified, update that pin to resolved and add a concise note describing the verified change. Use dismissed only when you have a concrete reason, and include it in the note. Leave the status unchanged when the fix is incomplete, uncertain, or unverified.

Fetching, reading, or diagnosing a report must never change its status. A status update is an explicit final workflow action performed through the Disbug CLI or MCP tool; it is not background automation. Keep pin notes attached to the pin they describe. Do not update the session status automatically, including when every pin is resolved or dismissed. Use the session status command or MCP tool only when the user explicitly requests a session-status change.

Read the full file on GitHub · 37 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. yesterday First seen · 37 lines · 23 tokens per session scan A f16ce5c13140

Subscribe to this mod's changes

using-disbug is a skill published in the GitHub repository disbug-io/disbug-cli (5 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 638 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.

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