📖About

Ninad requirement (2026-08-02): any agent asked in chat should advise whether a thing needs an initiative or can be done directly. The action boundary already lists what the agent CAN do and request_initiative (3522) already files with Elrond from chat; what is missing is the COUNSEL DOCTRINE in the common layer: record-vs-capability (a record change - persona, purpose, goals, a method skill - is a chat action; new capability - code, droids, schedules, tools, privileges, shared templates - is an initiative), stated in the shared handbook block every agent composes into its prompt, so the advice is uniform and correct estate-wide. Regression locks the doctrine into the composed handbook.

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• Current state at filing (Elrond validity check): Agents have an action boundary and request_initiative exists, but the shared handbook block does not yet carry a uniform record-vs-capability counsel doctrine. No completed work covers this specific advice layer, and no named subject is retired. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• [status-router] reviewing -> closed | event=operator_signoff | Auto-accepted (CAROL-INI-1859): Orion-initiated, >2 days in reviewing with no objection. (el-srac-01)

✅Success criteria

• The shared actions-handbook block every agent composes carries the initiative-vs-direct counsel doctrine: record changes via chat actions, capability changes via initiative, with request_initiative as the path it offers (must_have)
• Proven live: an agent chat asked for advice answers with the doctrine and does not invent abilities (must_have)
• A regression test locks the doctrine into the composed handbook for a sample of agents (must_have)