titan-appserver-bridge

Intent

Use this skill to prepare or inspect the Titan app-server bridge while keeping local agent execution visible and gated.

Trigger boundary

Use this skill when:

• a Titan console needs a JSON-RPC shaped bridge
• thread and turn events need normalization
• approvals, replay, or metrics need one bounded bridge state

Do not use this skill when:

• the request asks for hidden background agents
• the bridge would start hidden agent execution without an operator-visible plan
• role truth or memory truth would be moved into the bridge

Inputs

• workspace root
• bridge state path
• thread and turn identifiers
• event payloads or launch plan request
• approval and receipt refs

Outputs

• bridge plan or state summary
• normalized event candidates
• approval queue status
• replay or metrics summary
• explicit non-execution note

Procedure

1. identify the bridge thread, turn, receipt, and event sources
2. translate bridge state into inspectable JSON-RPC or equivalent relay state
3. keep approvals, metrics, and replay data subordinate to source events
4. refuse hidden agent execution or silent gate changes
5. return replay, approval, or owner-route follow-up needed before continuation

Contracts

• The skill is explicit-only and must not be invoked as hidden background behavior.
• Titan role, helper/control-plane, runtime implementation, memory, proof, and public-runbook authority stays in owner repositories: aoa-agents, aoa-sdk, abyss-stack, aoa-memo, aoa-evals, and 8Dionysus.
• Receipts, bridge ledgers, console state, replay artifacts, approval records, and memory records are witnesses or candidates, not final owner truth.
• Forge mutation and Delta judgment gates must remain distinct, operator-visible, and receipt-linked.
• Missing source refs, missing approval, missing validation, or unclear owner route must be named as stop conditions.

Risks and anti-patterns

• treating Titan vocabulary as permission to widen authority
• letting receipt, replay, console, or bridge state replace owner-repo evidence
• auto-approving Forge or Delta because a plan looks plausible
• promoting candidate memory, approvals, replay, or receipts into canon without owner review
• using the skill for an ordinary repo task that has no explicit Titan route

Verification

• confirm direct skill invocation or explicit Titan service-cohort request is present
• confirm lane, gate, source refs, and owner surface are named when relevant
• confirm Forge or Delta locked or allowed state matches recorded approval evidence
• confirm generated artifacts are marked witness, candidate, derived, or advisory rather than final truth
• confirm next validation, replay, repair, or owner-route follow-up is named before continuation

Technique traceability

Manifest-backed techniques:

• AOA-T-0045 from 8Dionysus/aoa-techniques at 3b1d5d623569aa4920b87280d0db0e911d2e29d5 using path techniques/history/history-artifacts/witness-trace-as-reviewable-artifact/TECHNIQUE.md and sections: Intent, Inputs, Outputs, Core procedure, Contracts, Risks, Validation
• AOA-T-0066 from 8Dionysus/aoa-techniques at 3b1d5d623569aa4920b87280d0db0e911d2e29d5 using path techniques/history/history-artifacts/transcript-replay-artifact/TECHNIQUE.md and sections: Intent, Inputs, Outputs, Core procedure, Contracts, Risks, Validation
• AOA-T-0043 from 8Dionysus/aoa-techniques at 3b1d5d623569aa4920b87280d0db0e911d2e29d5 using path techniques/instruction/capability-boundary/multi-source-primary-input-provenance/TECHNIQUE.md and sections: Intent, Inputs, Outputs, Core procedure, Contracts, Risks, Validation

Adaptation points

• Extract a Titan-specific reusable technique into aoa-techniques only after repeated reviewed evidence exists; do not add pending IDs as placeholders.
• Keep repo-local command examples in owner docs or examples rather than hard-coding them into skill law.
• If a Titan surface graduates from scaffold to reviewed or evaluated, add review evidence before changing status.