agentmods.dev

TraceBug-ai: Instructions file for Claude Code

CLAUDE.md

TraceBug-ai CLAUDE.md is an instructions file for Claude Code from prashantsinghmangat/TraceBug-ai. It costs 973 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code, describing TraceBug's layout, commands, rules, and development workflow. TraceBug is a local-first bug-capture tool with a browser extension, a TypeScript software library, and a command-line tool.

In plain words
What is it for?
Use it to guide code changes, find relevant directories, understand build and test commands, and avoid editing generated files directly.
Why use it?
It gives the coding agent the project context it needs before changing files. It also warns which files are generated and which project rules to follow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is prashantsinghmangat/TraceBug-ai's own configuration. It tells Claude Code how to work on TraceBug-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TraceBug-ai configures →

not rated 4repo 2d ago A scan 973 tokens original MIT
View source ↗ prashantsinghmangat/TraceBug-ai tracebug.dev
Reuse

Borrowing it

Nothing to install: this file belongs to prashantsinghmangat/TraceBug-ai. 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/prashantsinghmangat/TraceBug-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/prashantsinghmangat/TraceBug-ai

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.

agentmods badge for TraceBug-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prashantsinghmangat/tracebug-ai/claude-md/github.svg)](https://agentmods.dev/instructions/prashantsinghmangat/tracebug-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/prashantsinghmangat/tracebug-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/prashantsinghmangat/tracebug-ai/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.

agentmods 80×15 button for TraceBug-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/prashantsinghmangat/tracebug-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/prashantsinghmangat/tracebug-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 973 This file is loaded in full into every session.
When invoked 973 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00973 $0.00973
Opus 5.5 $0.00389 $0.00389
Sonnet 5.5 $0.00195 $0.00195
Haiku 4.5 $0.00097 $0.00097

Measured 4d ago against content hash 93d826b239ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

TraceBug-ai 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 4d 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TraceBug - project memory for Claude Code

Local-first bug-capture tool: MV3 browser extension + npm SDK + stdio MCP CLI. MIT. No backend.

Layout

  • src/ - SDK (TypeScript). Built with tsup into the extension bundle.
  • cli/ - MCP CLI entry (cli/bin.ts -> dist/bin.mjs, published as packages/tracebug/).
  • tracebug-extension/ - MV3 extension: manifest.json, background.js (service worker), content-script.js, offscreen.* (MediaRecorder), popup.*, player.*, tracebug-init.js. Packaged builds land in tracebug-extension/dist/{chrome,firefox}.
  • tracebug-extension/tracebug-sdk.js and tracebug-extension/tracebug-provider-api.js - both generated by npm run build (tsup). Never edit by hand. The second is the provider HTTP layer (src/providers/api.ts) bundled for the background service worker, which cannot import the page SDK.
  • tests/ - Vitest unit tests (e.g. tests/storage.test.ts). e2e/ - Playwright specs + .e2e.mjs scripts; benchmark at e2e/benchmark.mjs.
  • docs/ - user docs; docs/adr/ - architecture decisions (read the relevant ADR before changing architecture).
  • docs/launch/ - current launch work: STATE.md (where things stand - start here), PLAN.md (what's left), PROGRESS.md. The *-archive.md files are closed history; don't read them unless you need why.

Commands

  • All gates: node scripts/check.mjs (--full if extension files changed, --firefox at the end of a phase). One line per gate, full output only on failure. See the gates skill; don't run the npm scripts one by one.
  • Build SDK + extension bundle: npm run build (tsup; rewrites tracebug-extension/tracebug-sdk.js, then reload the unpacked extension)
  • Single test file: npx vitest run tests/storage.test.ts --reporter=dot | e2e: node e2e/<name>.e2e.mjs (run only the related suite)
  • Benchmark: node e2e/benchmark.mjs

Hard rules

  • No backend, no telemetry, no remote loads in exported .html (ADR 001, 002).
  • Zero runtime dependencies (ADR 005). MV3 only (ADR 004). MCP is stdio only (ADR 006).
  • Never add a manifest permission without asking. Removing or making optional is fine.
  • Keep storage invariants in docs/ticket-flow.md and tests/storage.test.ts: never evict saved tickets, verify writes before showing "Saved".
  • Keep Firefox 128+ working; branch on feature detection, not on user-agent strings.
  • In extension mode the SDK runs in the page's main world: page localStorage is readable by the host site. Never store secrets there.

Read the full file on GitHub · 43 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. 4d ago First seen · 43 lines · 973 tokens per session scan A 93d826b239ec

Subscribe to this mod's changes

TraceBug-ai CLAUDE.md is an instructions file published in the GitHub repository prashantsinghmangat/TraceBug-ai (4 stars, last pushed 2d ago), licensed MIT. It adds 973 tokens to every session, about $0.0039 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 2026-10-17.

Project management
Related

Other instructions, from other repositories

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 · 9,649 tokens

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 · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens