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 agents/rajkaria/boil-the-ocean/codexgit clone --depth 1 https://github.com/rajkaria/boil-the-oceanWrote 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.
[](https://agentmods.dev/agents/rajkaria/boil-the-ocean/codex)<a href="https://agentmods.dev/agents/rajkaria/boil-the-ocean/codex"><img src="https://agentmods.dev/badge/agents/rajkaria/boil-the-ocean/codex.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00851 |
| Opus 5 | $0.00000 | $0.00426 |
| Sonnet 5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade C, and why
CODEX scanned grade C with 2 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 4d 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 -- codex 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 -- codex How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boil the Ocean on OpenAI Codex CLI
Codex workers run through codex exec (Codex's non-interactive mode). The protocol
file does the behavioral work — no Codex-side plugin system needed.
Install
No clone needed:
curl -fsSL https://raw.githubusercontent.com/rajkaria/boil-the-ocean/main/install.sh | bash -s -- codex
Or from a clone:
git clone https://github.com/rajkaria/boil-the-ocean.git
cd boil-the-ocean
./install.sh codex
What this does:
| Piece | Where | What you get |
|---|---|---|
| Pointer block | ~/.codex/AGENTS.md |
Four lines teaching every Codex session: repos with .ocean/state.json have an active run; the protocol file is binding; state mutates only via ocean.sh |
| CLI | ~/.local/bin/ |
ocean, ocean-daemon |
The pointer is deliberately tiny (AGENTS.md loads into every session — tokens are rent). It exists so interactive Codex sessions respect a run in progress; the daemon's workers get the full protocol through their launch prompt regardless.
Usage
cd your-project
ocean init docs/SPEC.md --verify-cmd "pytest -q" --goal "ship v1"
OCEAN_AGENT=codex ocean-daemon doctor # preflight: checks the codex binary too
OCEAN_AGENT=codex ocean-daemon start
Watch: ocean-daemon logs · Stop: ocean-daemon stop · Sprint table: ocean status.
Permission mapping
OCEAN_PERMISSIONS |
Codex flags | Meaning |
|---|---|---|
safe |
--sandbox workspace-write |
Sandboxed writes inside the workspace, no network |
standard (default) |
--full-auto |
Workspace-write sandbox with full autonomy — the sweet spot |
yolo |
--dangerously-bypass-approvals-and-sandbox |
No sandbox at all — container/VM only |
Codex's own sandbox is a genuine advantage here: standard gives you an
OS-level-sandboxed autonomous worker, which is a stronger default posture than most
agents can offer.
Codex-specific configuration
| Var | Notes |
|---|---|
OCEAN_CODEX_BIN |
Binary name/path (default codex) |
OCEAN_MODEL |
Passed as -m (e.g. o4-mini for cheap sprints, a stronger model for fix passes) |
OCEAN_EXTRA_FLAGS |
Anything else codex exec accepts (e.g. --profile work) |
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.
- 4d ago First seen · 80 lines · 0 tokens per session scan C 3a0aa815c3d7
CODEX 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 851 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ciel-cloud-ops-guild
CIEL's elite cloud and DevOps guild. Specializes in AWS, GCP, Azure, K8s, Docker, and CI/CD automation.
ciel-data-guild
CIEL's elite data and storage guild. Specializes in SQL, NoSQL, ClickHouse, Kafka, and Data Architecture.
ciel-experience-guild
CIEL's elite design and experience guild. Specializes in UI/UX, animations, and accessibility.
ciel-intelligence-guild
CIEL's elite intelligence and ML guild. Specializes in Python systems, ML Ops, and AI integration.
ciel-mobile-guild
CIEL's elite mobile and PWA guild. Specializes in Swift, Kotlin, Flutter, and AR/VR development.
ciel-quality-guild
CIEL's elite quality and debugging guild. Specializes in refactoring, E2E testing, and API integrity.