assets/bootstrap/skills/harness-land/SKILL.md
Use when a tracked harness plan is already archived and the human has explicitly approved merge, so the agent should merge the PR and complete the required post-merge bookkeeping.
npx skillsauth add catu-ai/easyharness harness-landInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use land only after the plan is archived and a human has said it is time to merge.
Run harness status.
If state.current_node is not execution/finalize/await_merge, stop.
harness reopen --mode finalize-fix for narrow repair or
harness reopen --mode new-step when the change deserves a new step, and
then return to harness-execute.harness-execute.Re-read the Pre-Land scan in
../harness-execute/references/controller-truth-surfaces.md
so merge readiness, CI truth, and required bookkeeping are freshly checked.
Verify the PR still looks merge-ready.
Merge the PR.
Prefer Merge commit unless the human explicitly asks for a different
strategy.
Run:
harness land --pr <url> [--commit <sha>]
This records merge confirmation and enters required post-merge bookkeeping.
Finish the required post-merge bookkeeping before leaving land.
Finish local cleanup, branch sync, and any final remote follow-up.
Run:
harness land complete
Run this only after the required PR and issue bookkeeping is complete. This
records required post-merge bookkeeping completion, clears the current
candidate pointer, and
records the last landed archived plan so harness status returns to idle
with the landed context preserved in artifacts.
11. Sync local main, delete the feature branch if appropriate, and leave the
worktree clean.
harness land --pr <url>
after merge and harness land complete after the required bookkeeping so
status stops reporting the archived candidate as current work.land if the candidate is no longer valid; switch back to
harness-execute via harness reopen --mode <finalize-fix|new-step>.documentation
Use when acting as a dedicated reviewer subagent for one assigned harness review slot in an existing review round and you need to inspect the change, write structured findings, and submit them through `harness review submit`. This skill is only for reviewer subagents, not for the controller agent.
data-ai
Create or update a tracked harness plan once the direction is clear enough to execute. Use this when work needs a self-contained plan that a future agent can complete from the repository alone, without relying on discovery chat or hidden session memory.
testing
Use when a tracked harness plan has been approved and the controller agent should drive implementation, review, archive closeout, publish/CI/sync evidence work, and merge-readiness follow-up until the archived candidate is genuinely ready to wait for merge approval. This is the main controller skill for day-to-day execution after approval.
testing
Run interactive, Socratic discovery before planning or execution when the objective, boundaries, tradeoffs, success criteria, size, or workflow direction are unclear, or when archived work may need to reopen. Do not use for casual Q&A, simple repo orientation, status checks, or already-approved execution.