Whale AGENTS.md

Repository instructions for Whale, a Go command-line and terminal interface application. They describe where code belongs, how to build and test it, and the project's coding and testing expectations.

In plain words
What is it for?
Use them when developing Whale, especially when adding packages, running builds or tests, writing documentation, or preparing changes for review.
Why use it?
They give a coding agent the project-specific rules it needs before changing files. This reduces misplaced code, inconsistent style, and missed tests or checks.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/usewhale/whale/agents-md
Clone the repo
git clone --depth 1 https://github.com/usewhale/Whale

Made for: Codex, OpenCode.

Per session 691 This file is loaded in full into every session.
When invoked 691 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00691 $0.00691
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 2d ago against content hash b89eaa328ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Whale 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 2d 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.

AGENTS.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

Whale is a Go CLI/TUI agent. The entrypoint is cmd/whale. Most application code lives under internal/:

  • internal/ui/cli and internal/tui for Cobra commands and terminal UI
  • internal/agent for the turn loop, approvals, hooks, and tool orchestration
  • internal/tools for built-in tools such as shell, patch, file, and web actions
  • internal/app, internal/session, internal/memory, and internal/store for runtime state and persistence
  • internal/evals for replay and harness-based eval coverage
  • docs/ for user-facing configuration docs
  • scripts/smoke/ for live API smoke checks that require a real DeepSeek key

Keep new packages focused and place tests next to the code they cover.

Build, Test, and Development Commands

  • make build (or go build -o bin/whale . on Windows without Make) builds bin/whale with the repo-local .gocache
  • make run (or go build -o bin/whale . && ./bin/whale) builds and launches the interactive TUI
  • make test (or go test ./...) runs the full offline Go test suite
  • make test-tui (or go test ./internal/tui/...) runs the TUI-focused subset
  • make test-evals (or go test ./internal/evals/...) runs eval and replay tests
  • make clean removes bin/ and .gocache

Prefer Makefile targets on macOS/Linux. On Windows (where make is not available by default), use the equivalent go commands listed above. The .gocache directory is managed automatically so cache paths stay consistent regardless of which method you use.

Coding Style & Naming Conventions

Follow standard Go style: tabs for indentation, gofmt formatting, concise package names, and exported identifiers only when cross-package use is required. Prefer table-driven tests for behavior matrices. Name files by responsibility, such as tool_repair.go, model_test.go, or preferences_test.go.

Testing Guidelines

Tests use Go's testing package. Name tests TestXxx and keep them adjacent to the implementation. Prefer offline tests with temp dirs, fake providers, and deterministic fixtures; live network checks belong in scripts/smoke/. For user-visible CLI/TUI changes, add or update behavior-level tests, not just helper-unit coverage.

Read the full file on GitHub · 43 lines

Changes

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.

  1. 2d ago First seen · 43 lines · 691 tokens per session scan A b89eaa328ef8

Subscribe to this mod's changes

Whale AGENTS.md is an instructions file published in the GitHub repository usewhale/Whale (924 stars, last pushed 22d ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 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 2026-08-30.