What is bug-from-failure?

A structured bug report made from a failed software test or failure log.

Recording the affected feature, environment, severity, evidence, reproduction steps, and notes about possible causes or test flakiness.

It turns technical failure details into clear reproduction steps and a factual comparison of expected and actual behaviour.

How kint4/autoframe configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kint4/autoframe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kint4/autoframe/main/.claude/skills/bug-from-failure/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/kint4/autoframe

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kint4/autoframe/bug-from-failure/github.svg)](https://agentmods.dev/skills/kint4/autoframe/bug-from-failure)

Your own site

<a href="https://agentmods.dev/skills/kint4/autoframe/bug-from-failure"><img src="https://agentmods.dev/badge/skills/kint4/autoframe/bug-from-failure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kint4/autoframe/bug-from-failure"><img src="https://agentmods.dev/badge/skills/kint4/autoframe/bug-from-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 429 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00429
Opus 5.5	$0.00018	$0.00172
Sonnet 5.5	$0.00009	$0.00086
Haiku 4.5	$0.00005	$0.00043

Measured 2mo ago against content hash 0dda8dba983a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bug-from-failure 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 2mo 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.

.claude/skills/bug-from-failure/SKILL.md · 64 lines

What it actually says

/bug-from-failure — Failure to Bug Report

Type: Functional Description: Turns a test failure into a structured, shareable bug report with repro steps, severity, environment, and expected vs actual behavior.

Input Format

Any of:

A failing test name or spec path
A pasted failure log / stack trace / screenshot description
A description of what went wrong

Output Format

A structured bug report in markdown:

### Title
[concise summary]

**Severity:** Critical / High / Medium / Low
**Environment:** [browser, base URL, env]
**Feature / Area:** [feature]

**Steps to Reproduce**
1. ...

**Expected Result**
...

**Actual Result**
...

**Evidence**
[log excerpt / screenshot / trace reference]

**Notes**
[suspected cause, related tests]

Step-by-Step Instructions

Read the failing spec and its Page Object(s) to understand the intended behavior.
Extract the failure signal (assertion that failed, error, step that broke).
Before writing, confirm it's a real bug — if it looks like flake, route to /flake-check.
Derive concrete, numbered repro steps from the test's actions.
State expected vs actual clearly and factually.
Assign severity based on user impact (blocking flow = Critical/High; cosmetic/edge = Medium/Low).
Capture environment from playwright.config.ts / .env variables (never paste secret values).
Output the report in the format above, ready to paste into Jira / Linear / GitHub Issues.

Rules

Report behavior, not implementation.
Never include secret values from .env.
If the cause is flake, defer to /flake-check instead of filing a bug.

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.

2mo ago First seen · 64 lines · 46 tokens per session scan A 0dda8dba983a

Subscribe to this mod's changes

bug-from-failure is a skill published in the GitHub repository kint4/autoframe (8 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 429 once invoked, about $0.0002 per session on Opus 5.5. 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.

Debugging ai ai-tools api-testing end-to-end-testing load-testing playwright

agent-qa-knowledge

Use when asked what an agent-qa run did, why a step passed or failed, what a run's screenshots, console or network showed, what knowledge agent-qa learned or served, where a knowledge record came from, or which runs exist. Reads runs, evidence and knowledge through the agent-qa MCP tools or the agent-qa CLI with…

vostride/agent-qa · 92 tokens

agent-qa-debug-fix

Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.

vostride/agent-qa · 46 tokens

agent-qa-result-triage

Use when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs. Prefer agent-qa MCP run/artifact tools and produce evidence-backed triage.

vostride/agent-qa · 45 tokens

perf-profiler

Runtime performance analysis beyond Lighthouse — bundle size analysis, memory leak detection, HTTP load testing, resource optimization audit, and runtime CPU profiling. Use before launch or when investigating performance issues.

JansenAnalytics/claudex · 40 tokens

k6-load-testing

Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.

LiHongwei-cn/lihongwei-cn · 35 tokens

moli-webfetch

Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…

lexmount/moli · 90 tokens

autoframe: Skill for Claude Code