What is cowork--bug-reporter CLAUDE.md?

Instructions for turning a screen recording with spoken commentary into bug tickets. The workflow identifies each reported problem, transcribes the narration with word-level timing, captures matching evidence, requests approval, and creates tickets in an issue tracker.

Use it to report application bugs from video walkthroughs, with screenshots or clips linked to each ticket. The supplied setup is configured for Linear, an issue-tracking service.

It removes the manual work of watching a walkthrough, locating every issue, and attaching the right screenshots or video clips. It also defines the tracker, labels, environment settings, and review steps.

How cpinto/cowork--bug-reporter configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cpinto/cowork--bug-reporter. 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/cpinto/cowork--bug-reporter/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cpinto/cowork--bug-reporter

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/instructions/cpinto/cowork--bug-reporter/claude-md/github.svg)](https://agentmods.dev/instructions/cpinto/cowork--bug-reporter/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cpinto/cowork--bug-reporter/claude-md"><img src="https://agentmods.dev/badge/instructions/cpinto/cowork--bug-reporter/claude-md/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/instructions/cpinto/cowork--bug-reporter/claude-md"><img src="https://agentmods.dev/badge/instructions/cpinto/cowork--bug-reporter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,950 This file is loaded in full into every session.

When invoked 3,950 The same file — it is already loaded in full.

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	$0.03950	$0.03950
Opus 5	$0.01975	$0.01975
Sonnet 5	$0.00790	$0.00790
Haiku 4.5	$0.00395	$0.00395

Measured 9d ago against content hash fcef93d24d1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cowork--bug-reporter CLAUDE.md 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 9d 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.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug reporting from video walkthroughs

This project turns a screen recording with spoken commentary into tickets in an issue tracker, with screenshot or video evidence attached.

The user records a walkthrough of an application and says what is wrong as they go. You transcribe the narration with word-level timestamps, find every issue, cut the matching frame or clip, get approval, then create the tickets.

Configuration

Everything specific to one person's setup lives in this block. Change it here, not in the workflow below. Forks of this project are expected to edit it.

tracker:          Linear                       # the issue tracker tickets go to
tracker_mode:     script                       # script | mcp
tracker_adapter:  scripts/trackers/linear.py   # script mode only
tracker_notes:                                 # mcp mode only, path to a notes file
default_project:                               # blank means ask the user each time
default_labels:   Bug                          # applied to every ticket, if the label exists
session_timezone: Europe/London                # session folder names use this zone
whisper_model:    small                        # tiny | base | small | medium
transcribe_language:                           # blank means auto-detect

tracker_mode decides how step 7 works.

script: a command line adapter creates the tickets. Deterministic, and it uploads evidence files properly. This is the preferred mode.
mcp: you create the tickets yourself using the tracker's Cowork connector, following tracker_notes. Use this when no adapter exists for the tracker.

If the user asks to switch tracker, follow "Changing the tracker" below.

Ground rules

Never create a ticket before the user approves the issue list.
Never invent an issue the user did not state. The transcript is the source of truth. Screen content only supports what was said, it never adds new issues.
All work for one recording stays in one session folder. Do not mix sessions.
Every script is safe to run again. If a step fails, fix it and re-run.

Read the full file on GitHub · 415 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.

9d ago First seen · 415 lines · 3,950 tokens per session scan A fcef93d24d1c

Subscribe to this mod's changes

cowork--bug-reporter CLAUDE.md is an instructions file published in the GitHub repository cpinto/cowork--bug-reporter (2 stars, last pushed 27d ago), licensed MIT. It adds 3,950 tokens to every session, about $0.0198 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.

Debugging claude-ai claude-cowork claude-desktop claude-skills product-management workflow

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

cowork--bug-reporter: Instructions file for Claude Code