docs: frame project and agent workflow exploration

Record the reported navigation and coordination friction, verified native capabilities, and provisional workflow comparison. Keep proposed delegation and tool choices distinct from accepted decisions; collect workload, persistence and trial constraints together.

docs/constellation-work.md

@@ -122,13 +122,45 @@ The focus is the broader environment, not further API/database polish. Candidate
 areas remain places/ownership, navigation/interaction, human/agent collaboration,
 and system operation/maintenance; these are discussion areas, not a work queue.
 
-Agent-session navigation was the last open conversation: agent-deck is already
-installed (previously observed as 1.15.0). Its help offers native project sessions,
-search, attach and Ctrl+Q detach, with optional groups. No sessions were inspected
-or migrated. Start from the user's experience before changing bindings or selecting
-it over Herdr. Proposed roles: Walker enters places/apps, Niri navigates windows,
-and the session manager resumes agent work. Avoid duplicating its session list or
-imposing groups before use demonstrates a need.
+Current discussion: consistent project/agent work and Niri workspace use. The user
+values Herdr's spaces and overview of running/waiting agents, but dislikes its
+keybindings and mouse orientation. Agent-deck has startup issues (not diagnosed).
+Kitty/Niri, tmux and Zellij are candidates, not selected replacements.
+
+Read-only inspection found existing Niri overview, workspace movement and tabbed
+columns; Kitty has no declared project/session organization. Installed versions:
+Kitty 0.48.2, Niri 26.04, tmux 3.7c, Zellij 0.45.1 and Herdr 0.9.0.
+Herdr's installed default config confirms remappable navigation and agent jumps.
+Current [Herdr keyboard docs](https://herdr.dev/docs/keyboard/) describe direct
+chords; [Kitty sessions](https://sw.kovidgoyal.net/kitty/sessions/) supply native
+session creation/switching. Session layouts and window overviews do not themselves
+provide authoritative agent attention states. tmux detach keeps processes alive;
+Zellij resurrection recreates layouts/commands, not process memory. None of these
+capabilities was exercised interactively; no sessions were inspected or changed.
+
+Proposed workflow, awaiting discussion: organize human-visible work by project/task;
+one lead conversation owns each coherent change. Use bounded subagents when work
+is independent, with explicit ownership and evidence returned to the lead. Separate
+worktrees for independent writing efforts, one integration owner. Keep enduring
+repository rules in AGENTS.md, current goals/acceptance in task prompts, and durable
+decisions/current state in existing project docs. No fixed agent team is selected.
+
+Proposed comparison: hold the desktop and model settings fixed; compare solo,
+solo plus independent review, then bounded parallel delegation on the same starting
+commit and task. Record accepted correctness, unnecessary complexity, human
+interventions/rework, total completion time and aggregate usage including workers.
+Use fresh isolated runs and common acceptance checks; repeat promising variants
+before drawing reliability conclusions. Measure desktop navigation separately.
+[Codex subagents](https://learn.chatgpt.com/docs/agent-configuration/subagents)
+and [evaluation guidance](https://developers.openai.com/api/docs/guides/evaluation-best-practices)
+support bounded delegation and task-specific evaluation; the proposed trial is
+not a measured result. No benchmark framework or comparative runs created.
+
+Inputs requested together: typical project/agent count and clients; required
+persistence (project switch, terminal close, logout/reboot, remote connection);
+a representative trial task and rough time/spend limit. These determine the first
+concrete trial. No configuration changes, tests, activation or agent runs in this
+discussion; documentation whitespace checked.
 
 Mail search remains unresolved. The workbench's custom mail reader, inventory
 pilot, justfile and old README are archived; native Garden/kubectl/K9s now own the

docs/constellation.md

@@ -30,9 +30,16 @@ use a flake to declare its tools without Nix owning the surrounding workspace.
 - Outlook is acceptable as an application, but its interaction and integration
   do not fit as naturally. Accessible mail for tools and agents matters separately
   from choosing a mail reader. Preserve meaning and source context, not just text.
-- Herdr's persistent-agent concept fits; its shortcuts do not. Agent-deck is
-  already installed alongside Herdr; whether it fits through actual use remains
-  open. No replacement has been selected.
+- Herdr provides useful structure: spaces, running agents and visible attention
+  states. Its keybindings and mouse-oriented interaction fit poorly. Agent-deck
+  gave a poor first impression through startup issues; no replacement is selected.
+  Explore whether Niri/Kitty or a terminal multiplexer can provide a more composable
+  workflow while retaining that understandable overview.
+- Current friction is a lack of consistent project and agent working practices,
+  including Niri workspace use. Tool choice and agent collaboration need to be
+  considered together. Alignment, maintainability and human attention matter
+  alongside speed/cost; compare workflows through concrete tasks before adopting
+  a fixed delegation pattern.
 - Repositories should contain code and documentation needed by that code, not
   become containers for general notes and company material destined for Git remotes.
 - Company work includes repositories, reference material, notes, credentials and