Borrowing it
Nothing to install: this file belongs to fatihbaltaci/GoDrop. 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/fatihbaltaci/GoDrop/main/CLAUDE.mdgit clone --depth 1 https://github.com/fatihbaltaci/GoDropWrote 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/fatihbaltaci/godrop/claude-md)<a href="https://agentmods.dev/instructions/fatihbaltaci/godrop/claude-md"><img src="https://agentmods.dev/badge/instructions/fatihbaltaci/godrop/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 5.1 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
GoDrop CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
make build # binary into ./bin
make test # every test with the race detector
make cover # coverage, fails below 100%
make lint # go vet, gofmt check, shellcheck install.sh
make docs # regenerate everything that is generated (see below)
make run # dev server on 127.0.0.1:48080 with a throwaway token
make fuzz # the three input sanitiser fuzz targets, a minute each
make snapshot # build every release artefact locally, without publishing
One package, one test, one fuzz target:
go test ./internal/storage/
go test ./internal/cli/ -run TestInitNonInteractiveWritesEverything
go test ./internal/server/ -run "^$" -fuzz FuzzSanitizeExt -fuzztime 30s
The whole suite runs in about six seconds (eight with -race); anything much
slower than that is a bug in the test, not a reason to wait.
golangci-lint is not in the Makefile but CI runs it, pinned:
golangci-lint run ./... # v2.12.2, config in .golangci.yml
What CI enforces
- 100% statement coverage of
./internal/..., checked by the Quality gate job.cmd/godropis excluded deliberately: it is a wiring shim aroundos.Exit. When a branch is genuinely unreachable, delete it rather than lowering the bar; when it is reachable only through the filesystem, the OS or a clock, add a seam (a package-levelvarholding the function) and inject it from the test. Existing seams:now,randRead,finish,renameFile,osExecutable,lookup,lookPath,runCommand,listenOn,euid. gofmt,go vetfor linux/amd64, linux/arm64, darwin/arm64 and windows/amd64, govulncheck, shellcheck, actionlint,goreleaser check, and a YAML parse of the embedded OpenAPI document.- Tests on Linux, macOS and Windows. Windows is where path assumptions,
filepathversuspath, line endings and advisory file modes break; tests that depend on POSIX modes skip themselves there.
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.
- 7d ago First seen · 124 lines · 1,656 tokens per session scan A a7ded08c2f53
GoDrop CLAUDE.md is an instructions file published in the GitHub repository fatihbaltaci/GoDrop (1 stars, last pushed 9d ago), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 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
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.
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.
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).
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.