What problem does it solve? Sessions often end with claims of completed work that were never verified, producing phantom artifacts and narrated-as-done summaries. This Skill audits every completion claim made during a session and binds each one to checkable evidence before the final summary is written. ## Core Features & Use Cases - Claim harvesting and receipt binding: Sweeps the session transcript for every claim of done/fixed/exists/passes and attaches verifiable evidence such as commit hashes, pytest output, file paths, or spine receipt ids. - Structured disposition routing: Routes unreceipted claims to exactly one outcome — REGISTERED in docs/state/BROKEN_REGISTER.md, HANDED OFF with an exact next command, or RETRACTED as a corrected phantom. - Ledger receipt output: Writes a JSON ledger to ~/.dharma/session_ledgers/ and emits a LANDING LEDGER table in the final message that gates what the prose summary may claim. - Use Case: At the end of a coding session where you fixed tests, edited files, and pushed a branch, invoke this Skill to produce a ledger proving each claim with a commit hash or test run, retract anything unverified, and hand off remaining work with runnable next steps. ## Quick Start Tell the agent to land the plane and audit this session's claims into a receipted ledger before writing the final summary.
