Borrowing it
Nothing to install: this file belongs to antflydb/antfly. 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/antflydb/antfly/main/CLAUDE.mdgit clone --depth 1 https://github.com/antflydb/antflyWrote 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/antflydb/antfly/claude-md)<a href="https://agentmods.dev/instructions/antflydb/antfly/claude-md"><img src="https://agentmods.dev/badge/instructions/antflydb/antfly/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/antflydb/antfly/claude-md"><img src="https://agentmods.dev/badge/instructions/antflydb/antfly/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 | $0.00787 | $0.00787 |
| Opus 5.5 | $0.00315 | $0.00315 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
antfly 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 6d 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 — 60 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.
Worktrees and Build Caches
Work in a git worktree under .worktrees/<name> created from origin/main. Keep build caches inside that worktree, never in a temporary --cache-dir, and run make gc after long build sessions. Details are in @AGENTS.md.
Project Overview
What Antfly is, install options, and features are in README.md. Where things live:
zig/: the Antfly server (zig/pkg/antfly), storage engine shared with embedded Lite (zig/pkg/antfly-embedded), and inference runtime (zig/pkg/inference)go/: SDK, embedded bindings, and supporting libraries (managed operator/proxy code lives in Colony). Each module inGO_MODULES(Makefile) is independent; build it from its own directory withGOWORK=off GOEXPERIMENT=simd go(Make targets set this)ts/,py/,rs/: TypeScript packages and apps, Python SDK, Rust SDKspecs/openapi/: API source of truth;openapi.yamlat the root is generateddocs/: hand-written documentation, synced into colony/frontend/apps/www-antfly at build time
Read docs/architecture.mdx for the Raft, storage, and index design, and specs/openapi/antfly/indexes.yaml for index types and options. Don't rely on memory for either; both change often.
Commands
make build # Zig antfly binary, copied to ./antfly (run ./antfly standalone)
make generate # After OpenAPI or antfarm changes (Zig modules, joined openapi.yaml, Go/TS/Python/Rust SDKs, antfarm build)
make gc # Garbage-collect build caches across all worktrees
Testing
make zig-test
cd zig && make unit-test
uv run --project zig/e2e/antfly pytest -q
Long-running tests (E2E, evals, -race) should write output to a file:
cd zig && make test > /tmp/test.log 2>&1
uv run --project zig/e2e/antfly pytest -q > /tmp/test.log 2>&1
cd go/pkg/sdk && GOEXPERIMENT=simd go test -race -v ./... > /tmp/test.log 2>&1
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.
- 6d ago Changed · +5 tokens per session 755b48ad8591
- 13d ago Changed · -1 tokens per session e518b4b2c31b
- 16d ago Changed · -51 lines · -440 tokens per session b0197c190412
- 22d ago Changed · +1 tokens per session ce20e1e88e45
- 1mo ago Changed · -2 tokens per session c844759f84d7
- 1mo ago Changed · +125 tokens per session 89b911f49bdc
- 2mo ago First seen · 111 lines · 1,099 tokens per session scan A 6d25d4e16c9b
antfly CLAUDE.md is an instructions file published in the GitHub repository antflydb/antfly (478 stars, last pushed today), licensed Apache-2.0. It adds 787 tokens to every session, about $0.0031 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.