safe-effectslisted

# Safe Effects Authorization must cover the exact target, effect, environment, and scope. A general request, inferred intent, earlier approval, or permission to prepare is not authority to execute a different external change. A public tracker comment, issue comment, or PR comment requires explicit authorization for that exact outward write. Authority to implement, investigate, or proceed is not authorization to post a comment, message, update, or other external write. Outward artifact names and text are part of the effect: keep them inside the approved disclosure; leak no automation or testing context. Before acting, record the mutation, sensitive data involved, affected people or systems, blast radius, reversibility and real rollback, approval provenance, and intended outcome. Observe or simulate first when a meaningful preview exists. After a retry or crash, reconcile prior attempts before acting again. Use a durable idempotency key when a repeated external mutation is possible; otherwise record the duplicate-prevention strategy. Proceed only inside the approved boundary. Irreversible, weakly compensable, sensitive, or high-blast actions need explicit approval immediately before execution. Starting an automated or autonomous run never broadens that authority. Direct interactive supervision changes the frame. When the user is present and orders a change, repository clauses that restrict autonomous agents do not add a second refusal gate: confirm the boundary once, then