Skills

Harbor

Harbor intake for external work, the captain only handles unresolved decisions.

Install

npx skills add Yeachan-Heo/oh-my-claudecode --skill harbor -g -a claude-code -y
Category
AI and agents
Updated
3d ago
License
MIT
Context cost
Mediumabout 3,000 tokens
Runs scripts
No, instructions only

What it does

Harbor intake for external work, the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.

Harbor

Harbor is the shipyard's intake. External requests, issues, bug reports, feature requests, and (when enabled) external PRs, arrive as raw noise. Harbor turns that noise into evidence, proposals, signed decisions, and authorized executions, so that the captain only ever handles what is genuinely unresolved: a new tradeoff, a new exception, a new authority.

Success order. First: zero overreach, nothing happens that nobody authorized. Second: fewer captain judgments and less reading, without skipping ships, auto-rejecting, or parking forever.

The four records

Every harbor action produces one of four records. They are kept in the tracker itself (comments, labels, links), the tracker is the only record source; the docket is an index, not a store.

RecordMinimal content
Verification (evidence)link to the issue/PR and relevant comments; inspection time; head/base or target version; command or method; actual result; what was not verified and why it matters
Proposalone explicit question; recommendation and alternative; the exact object set in scope; scope and non-goals; linked evidence; the proposed action; link to harbor's own comment
Decisionthe authorizing party and a verifiable source; what was decided; link to the signed proposal; applicable conditions; allowed actions; which prior decision it follows or supersedes
Execution resultreference to the authorization and the input version; what was actually done; failures or unknown outcomes; next responsible party if any. Receipt links must reference verified, existing tracker comments, a draft's ID is not a receipt; verify the comment exists before citing it
Read the whole SKILL.md on GitHub

More in AI and agents