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.

ELISAResearch
Connecting

Agent 1

Judges one agent's delivered output against its written contract — the card, the charter, the acceptance criteria — and writes a pass or a finding.

Agent 1

Not connectedIdle — nothing queued

Output conformance review · Oversight (not in the ELISA spec)

oversight.agent_1

Profile charter name: Anurupa — 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
oversight-a1
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)

Judges one agent's delivered output against its written contract — the card, the charter, the acceptance criteria — and writes a pass or a finding.

Will not (declared, and enforced at the gate)

  • edit, reformat, rewrite or re-run the artifact under review (script-checkable: block every write, patch and execute call whose target is an artifact this agent is reviewing)
  • approve, publish, send or deploy anything, ever
  • review work produced by any agent in sector `oversight`, or work it previously advised on
  • write a verdict without naming the contract clause and the artifact field the verdict rests on
  • change the reviewed job's status; it writes a finding and the job's own gate honours it

Owns (record types)

  • conformance finding
  • conformance verdict record

Skills (declared)

No skills declared.

Skills deliberately withheld

  • security-reviewer — oversight.agent_6 owns it; conformance is contract-versus-output, not vulnerability hunting
  • research — oversight.agent_2 owns it; checking whether an external claim is true is a different job from checking whether the contract was met
  • humanizer — people.agent_6 owns it in People; a reviewer rewriting the text it reviews would be acting on its own judgement

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
edit, reformat, rewrite or re-run the artifact under review (script-checkable: block every write, patch and execute call whose target is an artifact this agent is reviewing)

Inputs (reads)

  • agent_result id
  • artifact id
  • contract or charter
  • acceptance criteria

Outputs (produces)

  • conformance finding
  • pass record
  • clause-by-clause verdict

Routing

Escalates to
oversight.orchestrator
Hands off to
oversight.orchestratoroversight.agent_2

Approval policy

Scoped write — may write, but only inside a defined boundary

Idle missions

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