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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/antflydb/antfly/agents-md"><img src="https://agentmods.dev/badge/instructions/antflydb/antfly/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/antflydb/antfly/agents-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 | $0.00444 | $0.00444 |
| Opus 5.5 | $0.00178 | $0.00178 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
antfly AGENTS.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.
What it actually says
AGENTS.md
Guidance for coding agents (Claude Code, Codex, and others) working in this repository. Project layout, commands, and testing live in CLAUDE.md.
Worktrees
-
Do branch work in a git worktree under
.worktrees/at the repository root, never in/tmp,~/.cache, or a sibling directory:git fetch origin git worktree add -b <branch> .worktrees/<name> origin/main -
Name the directory after the branch (
fix/foo-bar→.worktrees/fix-foo-bar). -
When the branch is merged or abandoned, run
git worktree remove .worktrees/<name>andgit worktree prune.
Build caches
Zig and Cargo never evict build output; one throwaway Zig cache reached 150 GB.
- Use the worktree's own caches:
.zig-cache/andzig-out/for Zig,rs/target/for Rust. Never point--cache-dir,ZIG_LOCAL_CACHE_DIR, orCARGO_TARGET_DIRoutside the worktree. - Never create a temporary cache directory (
mktemp,~/.cache/antfly-*,/tmp/...) for builds or tests. If a task needs an isolated cache, put it inside the worktree and delete it before finishing. - Reuse one
zig-outprefix instead of accumulatingzig-out-<variant>directories. - External conformance and recall fixtures are the one shared exception: they are immutable, hash-verified downloads cached once under
~/.cache/antfly/conformance-fixtures(the-Dconformance-fixturesdefault). Don't redirect them into/tmpor a per-task directory. - Run
make gcafter long build or test sessions and whenever disk space is low (make gc DRY_RUN=1previews). It cleans every worktree plus the Zig, Go, uv, and Node caches but skips anything a running build wrote in the last 30 minutes; seescripts/cache_gc.shfor the rules.
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 Changed · +1 lines · +61 tokens per session 0ff98e44c24f
- 16d ago First seen · 25 lines · 383 tokens per session scan A 14759b4199c8
antfly AGENTS.md is an instructions file published in the GitHub repository antflydb/antfly (478 stars, last pushed today), licensed Apache-2.0. It adds 444 tokens to every session, about $0.0018 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 2026-10-13.
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.