# Reconcile Claims To Landed

> Reconcile claimed work with repository, review, deployment, and artifact state without trusting status prose.

- Skill: `homenshum/reconcile-claims-to-landed` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add homenshum/reconcile-claims-to-landed`
- Raw SKILL.md: https://api.skillmd.com/api/skills/homenshum/reconcile-claims-to-landed/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: HomenShum (https://skillmd.com/u/homenshum)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/homenshum/reconcile-claims-to-landed

---


# Reconcile claims to landed state

Read [the execution contract](references/contract.json) before starting. Validate the final receipt with its parameterized `verification.argv`, replacing `{python}`, `{skill_dir}`, and `{receipt}` with concrete local values.

List each claimed outcome, then observe the corresponding branch, commit,
review, deployment, artifact, or live content signal. Classify it `PLANNED`,
`IMPLEMENTED`, or `PROVEN`; never promote from a report alone.

Return missing receipts, stale claims, conflicting owners, and the single next
action for each gap. Keep the sweep read-only unless the request explicitly
includes repairs. A successful push or CI log does not prove live content.

