workflow-bug-analysis

A step-by-step method for investigating software bugs and turning the findings into a structured GitHub issue.

In plain words
What is it for?
Use it to investigate error messages or unexpected behaviour, confirm a bug, trace it through the codebase, and document the result for GitHub.
Why use it?
It helps separate symptoms from root causes by reproducing the problem, tracing the relevant code, checking logs, and testing possible explanations.

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/sflandergan/agentic-coding/workflow-bug-analysis
Any agent
npx skills add sflandergan/agentic-coding --skill workflow-bug-analysis
Clone the repo
git clone --depth 1 https://github.com/sflandergan/agentic-coding

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 756 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 $0.00034 $0.00756
Opus 5 $0.00017 $0.00378
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00003 $0.00076

Measured yesterday against content hash 7d031ec91609, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-bug-analysis 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/create-bug-issue.sh, scripts/update-bug-issue.sh), 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.

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.

core/agents/skills/workflow-bug-analysis/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bugfix Analysis

Systematic investigation methodology for bug reports. The calling agent uses this skill to trace a bug from symptom to root cause and produce a structured GitHub issue.

Investigation Steps

1. Classify the input

Determine the input type and extract key signals:

  • Log/error input: stack trace, error message, HTTP status code. Extract: error message, stack trace frames, timestamps, affected module.
  • Behavior description: unexpected output, missing data, wrong calculation. Extract: expected vs. actual behavior, affected feature, reproduction hints.

2. Reproduce or confirm

Run the relevant test or code path to confirm the symptom exists:

  • Use the project's test commands (e.g. pnpm test, pnpm test:integration, or targeted test commands).
  • If no existing test covers the bug, add a temporary reproduction test or log statement, run it, and report the result.
  • Temporary working-tree changes must not be committed.

3. Trace the code path

Use @explore to map the affected code. Start from the error location or the described behavior and trace backwards to the root cause. Pay attention to:

  • Architecture boundaries between packages
  • Database queries and repository layers
  • Service dependencies and injection
  • Job orchestration and batch processing

Do not continue investigation from weak context — launch one or more explore subagents with focused questions. Multiple explore subagents may run in parallel when their questions are independent.

4. Inspect logs

When the bug involves runtime behavior, inspect the relevant logs. See docs/agents/bugfix.md for project-specific log locations and conventions.

  • Look for error and warning entries near the reported symptom time.
  • Match log levels to the project's conventions.

5. Form a hypothesis

Based on gathered evidence, state:

  • What you believe the root cause is
  • Why the evidence supports this conclusion
  • What alternative explanations were considered and ruled out

Read the full file on GitHub · 110 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. yesterday First seen · 110 lines · 34 tokens per session scan A 7d031ec91609

Subscribe to this mod's changes

workflow-bug-analysis is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 756 once invoked, about $0.0002 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