CLAUDE-CODE

CLAUDE-CODE is an agent for coding agents from rajkaria/boil-the-ocean. It costs 0 tokens per session (1,363 once invoked), scanned D, original, MIT.

An integration that adds the Boil the Ocean workflow to Claude Code, an agent-based coding environment.

In plain words
What is it for?
It is for starting, checking, stopping, and resuming Boil the Ocean runs in Claude Code, including runs stored in a project’s .ocean directory.
Why use it?
It provides automatic triggers, commands, lifecycle checks, scripts, and a command-line interface for managing long-running multi-sprint work.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the boil-the-ocean plugin — 1 skill, 3 commands, 4 agents, 2 hooks shipped together

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

Or install boil-the-ocean, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 4 agents, 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 CLAUDE-CODE

README.md
[![agentmods](https://agentmods.dev/badge/agents/rajkaria/boil-the-ocean/claude-code.svg)](https://agentmods.dev/agents/rajkaria/boil-the-ocean/claude-code)
Your own site
<a href="https://agentmods.dev/agents/rajkaria/boil-the-ocean/claude-code"><img src="https://agentmods.dev/badge/agents/rajkaria/boil-the-ocean/claude-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00000 $0.01363
Opus 5 $0.00000 $0.00681
Sonnet 5 $0.00000 $0.00273
Haiku 4.5 $0.00000 $0.00136

Measured 5d ago against content hash 4bb0e040cc05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

CLAUDE-CODE scanned grade D with 3 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/rajkaria/boil-the-ocean/main/install.sh | bash -s -- claude

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Hooks | `~/.claude/settings.json` | `Stop` → checkpoint guard, `SessionStart` → run announcer (idempotent merge, python3-validated) |

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/rajkaria/boil-the-ocean/main/install.sh | bash -s -- claude
docs/agents/CLAUDE-CODE.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boil the Ocean on Claude Code

Claude Code is the richest integration: native skill triggering, slash commands, and two lifecycle hooks that enforce the protocol mechanically.

Install

No clone needed:

curl -fsSL https://raw.githubusercontent.com/rajkaria/boil-the-ocean/main/install.sh | bash -s -- claude

Or from a clone:

git clone https://github.com/rajkaria/boil-the-ocean.git
cd boil-the-ocean
./install.sh          # default target is claude

What this does (all symlinks → your clone; git pull upgrades in place):

Piece Where What you get
Skill ~/.claude/skills/boil-ocean Auto-triggers on "boil the ocean", "build the whole spec", "do all the sprints", or resuming a repo with .ocean/state.json
Commands ~/.claude/commands/ /ocean <spec>, /ocean-status, /ocean-stop
Scripts ~/.claude/scripts/ ocean.sh, ocean-daemon.sh + the two hook scripts
Hooks ~/.claude/settings.json Stop → checkpoint guard, SessionStart → run announcer (idempotent merge, python3-validated)
CLI ~/.local/bin/ ocean, ocean-daemon

Plugin mode (alternative)

The repo is also a valid Claude Code plugin and its own one-plugin marketplace: .claude-plugin/plugin.json + .claude-plugin/marketplace.json + hooks/hooks.json (all wired through ${CLAUDE_PLUGIN_ROOT}). Install it from inside Claude Code with no shell and no clone:

/plugin marketplace add rajkaria/boil-the-ocean
/plugin install boil-the-ocean@boil-the-ocean

/plugin marketplace add registers this repo; /plugin install <plugin>@<marketplace> pulls it in (both names are boil-the-ocean, hence the doubled token). That wires the boil-ocean skill, the /ocean* commands, and both hooks. Re-running /plugin install updates in place.

The same manifest installs on other agents that speak the plugin-marketplace protocol — agy plugin install https://github.com/rajkaria/boil-the-ocean (Antigravity), droid plugin marketplace add … + droid plugin install boil-the-ocean@boil-the-ocean (Factory Droid), copilot plugin marketplace add rajkaria/boil-the-ocean + install (GitHub Copilot CLI).

Read the full file on GitHub · 124 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. 5d ago First seen · 124 lines · 0 tokens per session scan D 4bb0e040cc05

Subscribe to this mod's changes

CLAUDE-CODE is an agent published in the GitHub repository rajkaria/boil-the-ocean (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,363 tokens. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.