Borrowing it
Nothing to install: this file belongs to quailyquaily/aqua. 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/quailyquaily/aqua/master/AGENTS.mdgit clone --depth 1 https://github.com/quailyquaily/aquaWrote 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/quailyquaily/aqua/agents-md)<a href="https://agentmods.dev/instructions/quailyquaily/aqua/agents-md"><img src="https://agentmods.dev/badge/instructions/quailyquaily/aqua/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/quailyquaily/aqua/agents-md"><img src="https://agentmods.dev/badge/instructions/quailyquaily/aqua/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 | $0.00567 | $0.00567 |
| Opus 5.5 | $0.00227 | $0.00227 |
| Sonnet 5.5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
aqua AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
cmd/aqua/main.go: CLI entrypoint (aqua) and command wiring.aqua/: core Aqua domain logic (identity, contacts, RPC, node/session behavior).internal/fsstore/: file-backed storage primitives (atomic writes, JSON/JSONL helpers, locks, indexing).docs/: operator-facing docs (architecture.md,cli.md).- Tests live next to implementation files and use
*_test.go.
Build, Test, and Development Commands
go build -o ./bin/aqua ./cmd/aqua: build the CLI binary.go run ./cmd/aqua --help: run locally without a manual build.go test ./...: run all unit tests (baseline check before every PR).go test -race ./...: run race detector for concurrency/storage-sensitive changes.go test ./aqua -run TestExtractRPCIDForError: run a focused test during iteration.
Tip: isolate local state during manual testing:
AQUA_DIR=$(mktemp -d) go run ./cmd/aqua init
Coding Style & Naming Conventions
- Language target is Go (
go.moduses Go 1.24.x); always format withgofmt. - Follow Go naming: exported identifiers in
PascalCase, internal helpers incamelCase. - Keep package names short/lowercase (
aqua,fsstore) and files organized by concern (*_test.gomirrors production files). - Prefer wrapped errors with context (
fmt.Errorf("...: %w", err)), especially at storage/network boundaries.
Testing Guidelines
- Use the standard
testingpackage with clearTest...names describing behavior. - Prefer table-driven tests plus
t.Run(...)for variants. - Use
t.Parallel()where safe andt.TempDir()for filesystem isolation. - Cover both success and failure paths (invalid input, decode errors, lock/path failures).
Commit & Pull Request Guidelines
- Use Conventional Commits (for example:
feat(aqua): add protocol history lookup,fix(fsstore): reject invalid lock key). - Keep commits scoped and include related tests/docs in the same change.
- PRs should include: purpose, impacted paths, test commands run, and linked issue (if any).
- For CLI behavior changes, include sample command/output snippets in the PR description.
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 · 42 lines · 567 tokens per session scan A 512d873987b4
aqua AGENTS.md is an instructions file published in the GitHub repository quailyquaily/aqua (259 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 567 tokens to every session, about $0.0023 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.
aqua AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aqua AGENTS.mdquailyquaily/aqua | Instructions file | 259 | 7mo ago | Apache-2.0 | A | 567 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |