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.
npx agentmods add instructions/apps-in-toss-community/debugger/claude-mdgit clone --depth 1 https://github.com/apps-in-toss-community/debuggerWrote 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.
[](https://agentmods.dev/instructions/apps-in-toss-community/debugger/claude-md)<a href="https://agentmods.dev/instructions/apps-in-toss-community/debugger/claude-md"><img src="https://agentmods.dev/badge/instructions/apps-in-toss-community/debugger/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02414 | $0.02414 |
| Opus 5 | $0.01207 | $0.01207 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
debugger 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file is self-sufficient: everything a contributor needs to work in this repo lives here. It does not link to any private/internal repository — such links would 404 for outside contributors, which is worse than no link at all.
Project character (tone rules)
apps-in-toss-community is a community project with no affiliation to Toss / Apps in Toss. In every user-facing artifact (README, UI copy, package descriptions, commit/PR messages, code comments, chat responses, etc.) never use words like "official", "provided by Toss", "made by Apps in Toss", "powered by Toss", or anything else implying partnership, sponsorship, or endorsement by Toss. Use natural alternatives instead — "community", "open-source". When in doubt, omit the claim entirely.
Tone guide (no defensive disclaimers): state the identity once, plainly, in the README footer — Korean README.md: 커뮤니티 오픈소스 프로젝트입니다., English README.en.md: Community open-source project.. Do not use defensive phrasing like "not affiliated" / "unofficial" / "비공식". Do not use a > blockquote box right after a header, ⚠️ icons, bold emphasis, or repeat the disclaimer more than once per file. Never mix Korean and English in the same document — i18n means separate files (README.md ko primary + README.en.md en sub), not bilingual sections. Both files are equal canonical documents: same section order, and a change to one updates the other in the same PR. Technical caveats ("not a blessed API", "may break") are not disclaimers — fold them into the relevant feature description instead.
Issues, proposals, and feature requests all go through GitHub Issues.
Project overview
debugger is a pnpm workspace holding the remote-debugging half of what used to be a single, overgrown @ait-co/devtools package. devtools grew to cover 8 feature surfaces (mock SDK, browser dev env, phone preview, on-device debug, remote CDP, MCP server, test runner, in-app console) in one package. It is being split into 3 packages across 2 repos:
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.
- 3d ago First seen · 98 lines · 2,414 tokens per session scan A ce662e5b1b9e
debugger CLAUDE.md is an instructions file published in the GitHub repository apps-in-toss-community/debugger (0 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 2,414 tokens to every session, about $0.0121 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.