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.
npx agentmods add instructions/usewhale/whale/agents-mdgit clone --depth 1 https://github.com/usewhale/WhaleWhat 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 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
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.
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/cliandinternal/tuifor Cobra commands and terminal UIinternal/agentfor the turn loop, approvals, hooks, and tool orchestrationinternal/toolsfor built-in tools such as shell, patch, file, and web actionsinternal/app,internal/session,internal/memory, andinternal/storefor runtime state and persistenceinternal/evalsfor replay and harness-based eval coveragedocs/for user-facing configuration docsscripts/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(orgo build -o bin/whale .on Windows without Make) buildsbin/whalewith the repo-local.gocachemake run(orgo build -o bin/whale . && ./bin/whale) builds and launches the interactive TUImake test(orgo test ./...) runs the full offline Go test suitemake test-tui(orgo test ./internal/tui/...) runs the TUI-focused subsetmake test-evals(orgo test ./internal/evals/...) runs eval and replay testsmake cleanremovesbin/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.
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.
- 2d ago First seen · 43 lines · 691 tokens per session scan A b89eaa328ef8
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.
Other instructions, from other repositories
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
zot AGENTS.md
Instructions for patriceckhart/zot, covering working agreement for zot, product intent, starting a task, code ownership map and correctness contracts.
Tianshu-harness CLAUDE.md
Instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
phi AGENTS.md
Instructions for pulseaiclub/phi, covering phi, communication preferences, constraints, contributor guidelines and commands.
pi-go CLAUDE.md
Instructions for dimetron/pi-go, covering claude.md — pi-go, work in a git worktree, not the primary checkout, where worktrees live, what pi-go's agent already does, and why it matters and commits: all commits must be signed.
cocode AGENTS.md
Instructions for cocode-agency/cocode, covering agents.md, 仓库布局, 仓库边界, cocode-gui/ and cocode-tui/.