boil-the-ocean: Instructions file for Claude Code

CLAUDE.md

boil-the-ocean CLAUDE.md is an instructions file for Claude Code from rajkaria/boil-the-ocean. It costs 1,312 tokens per session, scanned A, original, MIT.

Project instructions for boil-the-ocean, an autonomous system that runs coding agents across multiple development sprints. They describe its current release, architecture references, worker protocol, tests, and installation details.

In plain words
What is it for?
Use them when developing, testing, or releasing boil-the-ocean. They point to the architecture and protocol documents, describe its offline test command, and record its plugin marketplace setup.
Why use it?
They give agents the project context and rules needed to change or release the system without disrupting its worker process or packaging.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex; built for gstack.

This is rajkaria/boil-the-ocean's own configuration. It tells Claude Code how to work on boil-the-ocean itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything boil-the-ocean configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rajkaria/boil-the-ocean. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rajkaria/boil-the-ocean/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rajkaria/boil-the-ocean

Made for: Claude Code.

Wrote 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.

agentmods badge for boil-the-ocean CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rajkaria/boil-the-ocean/claude-md/github.svg)](https://agentmods.dev/instructions/rajkaria/boil-the-ocean/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rajkaria/boil-the-ocean/claude-md"><img src="https://agentmods.dev/badge/instructions/rajkaria/boil-the-ocean/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.

agentmods 80×15 button for boil-the-ocean CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rajkaria/boil-the-ocean/claude-md"><img src="https://agentmods.dev/badge/instructions/rajkaria/boil-the-ocean/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,312 This file is loaded in full into every session.
When invoked 1,312 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01312 $0.01312
Opus 5 $0.00656 $0.00656
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 10d ago against content hash c71b31ba25c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

boil-the-ocean CLAUDE.md scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

installation overhaul modeled on gstack (github.com/garrytan/gstack) — curl-pipe
CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

boil-the-ocean — project notes for Claude Code

Autonomous multi-sprint execution harness for coding agents. Read README.md for the product story; docs/ARCHITECTURE.md before touching scripts/; the worker protocol is skills/boil-ocean/SKILL.md (protocol changes require a pressure-scenario re-test — see CONTRIBUTING.md rule 4). Tests: bash tests/test-ocean.sh (offline, zero tokens).

Current state (2026-07-13)

  • v1.2.0 released — merged to main ff-only (tip 74941ec), tag v1.2.0 + GitHub release published, .claude-plugin/marketplace.json live on the default branch so /plugin marketplace add rajkaria/boil-the-ocean resolves (verified: default branch is main, manifest is valid JSON there, source: "./" → plugin.json v1.2.0). One-click plugin install: /plugin marketplace add rajkaria/boil-the-ocean + /plugin install boil-the-ocean@boil-the-ocean from inside Claude Code, no shell/clone; same manifest installs on Antigravity / Factory Droid / Copilot CLI. Plugin entry carries no version (inherits from plugin.json), so release checklist stays VERSION + plugin.json. 86/86 tests (4 new in v1.2.0: marketplace.json validity + name/source resolution). CONTRIBUTING release checklist expanded (ff-to-main, tag+push, gh release, marketplace smoke-verify). Docs: README Install §, docs/agents/CLAUDE-CODE.md § Plugin mode, CHANGELOG.
  • v1.1.0 shipped to prod (commit 418fcb5 on main, tag + GitHub release published): installation overhaul modeled on gstack (github.com/garrytan/gstack) — curl-pipe bootstrap, install.sh auto agent detection, VERSION + ocean version --check (HEAD-SHA-pinned raw fetch, offline-safe, bash-3.2 semver compare since BSD sort lacks -V), ocean upgrade (ff-only pull + replay of recorded install targets), doctor PATH/update checks. Deliberately NOT adopted from gstack: telemetry, snooze, team mode.
  • v1.0.0 shipped: https://github.com/rajkaria/boil-the-ocean — tag + GitHub release published, CI green on macOS + Ubuntu.
  • Installed on this machine: ocean / ocean-daemon at ~/.local/bin (symlinks to this clone); ocean-daemon doctor passes clean.
  • Born in burn-rate (branch claude/boil-ocean-skill-baa5ea), fully extracted — no references remain in that repo's files.

Read the full file on GitHub · 73 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. 10d ago First seen · 73 lines · 1,312 tokens per session scan A c71b31ba25c5

Subscribe to this mod's changes

boil-the-ocean CLAUDE.md is an instructions file published in the GitHub repository rajkaria/boil-the-ocean (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens