ocean

ocean is a command for Claude Code from rajkaria/boil-the-ocean. It costs 19 tokens per session (208 once invoked), scanned A, original, MIT.

A command for starting or resuming an autonomous, multi-sprint project run that continues working from a written specification and saved state.

In plain words
What is it for?
Launching a new run from a file or description, resuming an existing run, and arranging scheduled execution through its daemon.
Why use it?
It lets a coding agent keep executing a large task across sessions while retaining its plan and decisions.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the boil-the-ocean plugin — 1 skill, 3 commands, 2 hooks shipped together

Good fit Launching a new run from a file or description, resuming an existing run, and arranging scheduled execution through its daemon.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rajkaria/boil-the-ocean/ocean
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.

Clone the repo
git clone --depth 1 https://github.com/rajkaria/boil-the-ocean

Made for: Claude Code.

Or install boil-the-ocean, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 2 hooks.

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 ocean

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/rajkaria/boil-the-ocean/ocean"><img src="https://agentmods.dev/badge/commands/rajkaria/boil-the-ocean/ocean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 208 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00019 $0.00208
Opus 5 $0.00010 $0.00104
Sonnet 5 $0.00004 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 9d ago against content hash be8673dcb4f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ocean 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 9d 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.

commands/ocean.md · 18 lines

What it actually says

Use the boil-ocean skill and follow it exactly.

  • If .ocean/state.json exists in this repo, resume that run (read state, plan, and decision journal first — they are the run's only memory).
  • Otherwise start a new run with the spec given in the arguments below: a file path, or an inline description (save inline text to .ocean/SPEC.md before ocean.sh init).

After the plan is committed and sprint 1 is underway, remind the user once, in one line: to keep this run alive across session/usage limits they can run the scheduler — bash <boil-ocean>/scripts/ocean-daemon.sh start from the repo root (install-launchd to also survive reboots). Then keep working; do not wait for a reply.

Spec / arguments: $ARGUMENTS

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. 9d ago First seen · 18 lines · 19 tokens per session scan A be8673dcb4f4

Subscribe to this mod's changes

ocean is a command published in the GitHub repository rajkaria/boil-the-ocean (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 208 once invoked, about $0.0001 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 2026-08-31.