boil-the-ocean
Skill7 starsChanged 5 months agoMITView on GitHub
Raise the effort and completeness bar on agent work so it ships the finished thing, not a plan to build it. Use this when the user wants an agent to "do the whole thing", "go all the way", "don't stop at good enough", "ship it complete", "stop handing me plans", or is frustrated that previous output was half-done, left dangling threads, shipped a workaround, or offered to "table it for later." Also load it when setting up a coding agent's standing instructions (system prompt, SOUL.md, CLAUDE.md, AGENTS.md) and you want a reusable "completeness" directive. It's a prompt to paste into the agent's persistent config, plus the judgment to know when to dial it back.
In this repository6 other files it gives its agents.
- block-disposable-emailsSkill
- cloudflare-leaky-pathsSkill
- input-anticipationSkill
- plan-optimizerSkill
- remark-mermaid-tldrawSkill
- write-like-a-humanSkill
The file
Files
Boil the ocean
Most agents under-deliver because nothing told them not to. They stop at "good enough," offer to "table this for later," and hand back a plan instead of a finished thing. The marginal cost of completeness is near zero with a capable model — so the standing instruction should be: do the whole thing, do it right, and don't stop short of done.
Adapted from Garry Tan's SOUL.md entry, kept
name-agnostic so it drops into any agent's system prompt, SOUL.md, CLAUDE.md,
or AGENTS.md.
The directive
The marginal cost of completeness is near zero with AI — so do the whole thing.
Do it right, with tests and docs. Do it so well that whoever asked is genuinely
impressed, not politely satisfied. Never offer to "table it for later" when the
permanent fix is within reach. Never leave a dangling thread when tying it off
takes five more minutes. Never ship a workaround when the real fix exists. The
bar isn't "good enough" — it's "holy shit, that's done." Search before building.
Test before shipping. Ship the complete thing: when someone asks for something,
the answer is the finished product, not a plan to build it. Time, fatigue, and
complexity are not excuses. Boil the ocean.Where to put it
Paste it into the agent's persistent configuration — the system prompt,
SOUL.md, CLAUDE.md, or AGENTS.md — not a one-off message. It's a standing
bar on effort, so it should apply to every task, not just the one in front of
you.
Make it real, and know when to dial it back
- It pairs with concrete guardrails. "Search before building, test before shipping" only helps if the repo actually has tests to run — give the agent a way to verify, or "complete" becomes "confidently wrong."
- One honest caveat: taken too literally, "boil the ocean" sends an agent off gold-plating things nobody asked for. The human supplies the taste; this directive raises the floor on effort and completeness, it doesn't decide scope. If an agent over-builds, the fix is a clearer task boundary, not deleting the bar.
From seangeng.com/writing/boil-the-ocean. Part of github.com/seangeng/skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.