Borrowing it
Nothing to install: this file belongs to ngthluu/loope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ngthluu/loope/main/CLAUDE.mdgit clone --depth 1 https://github.com/ngthluu/loopeWrote 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/ngthluu/loope/claude-md)<a href="https://agentmods.dev/instructions/ngthluu/loope/claude-md"><img src="https://agentmods.dev/badge/instructions/ngthluu/loope/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.
<a href="https://agentmods.dev/instructions/ngthluu/loope/claude-md"><img src="https://agentmods.dev/badge/instructions/ngthluu/loope/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00339 | $0.00339 |
| Opus 5.5 | $0.00136 | $0.00136 |
| Sonnet 5.5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
loope 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 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.
What it actually says
CLAUDE.md
Project instructions for the loope issue-processing daemon.
Lessons learned
On failure, continue from existing state — don't delete and restart from zero
When a step fails (a git worktree add, a pipeline run, a resume), prefer recovering and continuing from whatever already exists over deleting it and starting from scratch. Blowing away state on every failure throws out partial progress and, worse, can create infinite retry loops when the failure recurs each cycle.
This is a general working principle, not just a failure-recovery rule: never remove and start from zero — always try to build on what already exists. Reusing existing state saves tokens and effort; recreating it from scratch wastes both. Reach for existing artifacts, partial results, and prior work before regenerating anything.
Concretely:
- If a worktree still exists on the path, reuse it and continue working on it. Only reclaim (delete) a leftover when it is truly unusable — e.g. a bare orphaned branch whose worktree is gone.
- Reclaim/force-delete only as a last resort, gated on the specific condition that makes reuse impossible, not as the default reaction to any error.
- Keep the happy path untouched: recovery logic belongs in the error branch, so a normal run never pays for it.
See Worktree.Create in worker/infra/worktree.go for the pattern: try the operation; on
failure, reuse the existing worktree if present, otherwise reclaim the bare
leftover and retry once.
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 · 34 lines · 339 tokens per session scan A 8be078111a78
loope CLAUDE.md is an instructions file published in the GitHub repository ngthluu/loope (13 stars, last pushed 2mo ago), licensed MIT. It adds 339 tokens to every session, about $0.0014 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 2026-08-30.
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).
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.
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).
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 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.