Pre-dispatch rejection ledger MCP
Witness for MCP calls rejected pre-dispatch: hash-chained ledger, enum differ, signed receipts.
Entries whose own description does not support a confident category. They stay listed and searchable; we do not guess a category to make the grid look complete.
Witness for MCP calls rejected pre-dispatch: hash-chained ledger, enum differ, signed receipts.
Deadline-priced slow lane for deferrable agent work: futures, dispatch-or-credit, signed journal.
Checkpoint-paired twin trials for agent fleet changes with blinded verdicts.
Multilateral barter netting for agent services: cycles and chains cleared in kind, zero money.
Signed MCP host behaviour profiles: timeouts, refresh, retries.
Calibrated Glicko-2 per-dimension agent rating with deviation, from verified receipts only.
Salvageability triage for agent fleets in a declared mass-failure mode.
Personal-lock maintenance isolation for agent infrastructure: hasp-quorum refusal + try-start proof.
Live-payload conformance probes with signed receipts: ABSENT/EMPTY/PARTIAL/COMPLETE/BROKEN.
Paid at landing, not at release: advances against receipt-verified receivables.
In-band MCP sleeper sentinel — mid-session diff and quarantine inside your own client's session.
Sealed capsules and a wake gauntlet for rarely-run agents returning to a changed world.
Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.
Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.
Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof
Real MCP handshake witness graded per-client, signed expiring receipt.
Signed receipts + horizon statements proving whether an event-triggered agent actually woke.
Compensation registry for agent actions: inverses registered before effects land, with rewind
Cross-session fatigue ledger for agents: FIT/CAUTION/GROUNDED dispatch gating.
Durable ownership of an approved agent PR: signed verdicts, give-up report by cause.
Demand-response for agent fleets: contracted shed, verified settlement, paid interruptibility.
Meters agent-fleet acceptance capacity per operator and triages what lands.
Compares declared agent access against actual enforcement per identity class, with drift watch.
Your coding agents are isolated in worktrees; your breakage is not.