Mixed freshness. Depending on the panel, rows here are read live from elisa-core or come from a frozen copy of ELISA’s local store taken on 22 October 2026 — each panel says which, underneath itself. No agent is running.

ELISAPeople
Connecting

Agent 5

Owns the people policy set, the retention and consent record, and the decision of who may see which people field.

Agent 5

Not connectedIdle — nothing queued

Policy, consent & people-record custody · People + HR

people.agent_5

Profile charter name: Maryada — a label from the Hermes profile. Nothing routes on it; routing is by id only.

Measured — state right now

Idle — nothing queued. A profile exists, its queue is empty and nothing is pending. Idle describes the queue, not a live process. This UI is not connected to a running agent and never starts one.

Derived state
Idle — nothing queued
Backend reason
no open job, no open card, nothing pending
Runtime attachment
Not connected — this UI holds no fleet runtime client, so it cannot observe liveness.
Hermes profile
people-a5
Profile built
Yes
Runtime lock
Not locked · sector dispatchable: yes
May create its own cards
No
Spec source
specs/governance.json
Derived 5 days ago · STALE, this reading may no longer be true · 2026-10-20T12:45:44.000Zfrom elisa.db:agents.runtime_locked+sectors.runnable (via dispatchable()) · elisa.db:approvals.status='pending' · elisa.db:jobs.status · kanban.db:tasks.status (assignee=profile)

Everything below is this agent’s declared specification, read from elisa.db. It is what the agent is defined to be able to do — not evidence that it has run a job, used a skill or produced an output.

Mission (declared)

Owns the people policy set, the retention and consent record, and the decision of who may see which people field.

Will not (declared, and enforced at the gate)

  • delete a people record, consent record or retention log; it schedules an expiry and a human executes it (script-checkable: block any delete call against a people-owned record type for this agent)
  • grant itself or any agent a widened view of people data; it writes a boundary exception request and the orchestrator plus a human decide
  • approve its own boundary exception request
  • publish a policy document outside the People boundary without an approval token
  • weaken an existing retention or consent rule to unblock another agent's job

Owns (record types)

  • policy document
  • consent record
  • retention schedule
  • boundary exception request
  • access revocation list

Skills (declared)

No skills declared.

Skills deliberately withheld

  • security-auditor — oversight.agent_3 owns it. A custodian auditing its own boundary is the judge-and-actor problem in miniature; it declares the rule and oversight checks it holds
  • note-taking — operations.agent_2 owns it, and a policy is a people record that must not live in a shared notes store

Jobs (declared job types)

No job types declared.

MCP requirements

No MCP server required.

Persona (declared)

Communication
see this profile's SOUL.md
Reasoning
see charter.json -> contract and spec.will_not
Pushback
delete a people record, consent record or retention log; it schedules an expiry and a human executes it (script-checkable: block any delete call against a people-owned record type for this agent)

Inputs (reads)

  • people record set
  • policy requirement
  • retention period
  • release request

Outputs (produces)

  • policy document
  • consent record
  • retention schedule
  • boundary exception request
  • revocation list

Routing

Escalates to
people.orchestrator
Hands off to
people.orchestratorpeople.agent_3oversight.agent_3

Approval policy

Approval required — every action waits on a human decision

Idle missions

None. This agent does nothing unprompted — there is no idle mission to run.