settled-reach/docs/sprints/sprint-29/copy.md

Sprint 29: Body Catalog — Copy Team Briefing

Sprint goal: Complete body catalogs for all 258 remaining systems across all corridors. Agents: Miri (naming), Paula (narrative review), Ozzie (astrophysical + experience review) Scope: 258 systems, hops 4-12, all 5 corridors

Pipeline

Each system follows the /atlas author-system pipeline:

1. Read wiki (index.md + gttr.md) — build context
2. Generate astrophysical skeleton — tooling/atlas author "{system_id}"
3. Spawn Miri for naming — wiki-derived register, collision avoidance
4. Paula narrative review — names, population, stations vs wiki coherence
5. Paula + Ozzie dual review — narrative integrity + astrophysical sanity
6. Integrity check — automated verification
7. Commit — one system per git commit

See .claude/skills/atlas/references/author-system.md for full details.

STRICT: One system at a time. Complete the full pipeline (steps 1–7) for a single system before starting the next. Do NOT batch systems for writing, naming, or review. Batching causes agent context overflow, cross-system bleed in review feedback, and review agents getting stuck on oversized payloads. Each system must be isolated in the review agents' context windows — send one system to Miri, get names back and apply them, send to Paula and Ozzie, get reviews back and fix issues, verify, commit, then move to the next system. Between systems, clear reviewer agent contexts (shutdown + respawn, or user-initiated context clear) to prevent accumulated review data from prior systems causing bleed or context pressure in the next review cycle.

Agent spawn requirements:

• All spawned agents (Miri, Paula, Ozzie) must be instructed to read .claude/skills/atlas/SKILL.md and the relevant review reference (e.g. references/review-ozzie.md) on first activation.
• Inhabited planets should have their OWN name, distinct from the system name. Only match when the wiki explicitly uses the same name for both.
• Secondary stations (commercial, research, agricultural, industrial) must reflect institutions described in the wiki — not every system is horizon-only.
• Occasional rural moons (small, single-function: mining, fungi growing, ore processing — a few hundred to ~1K people) add variety.

Work Order

Process by corridor, hop-order within each corridor (closest to Gateway first). All tracks run in series on the copy branch (parallel worktree approach superseded).

Track	Story	Corridor	Systems	Hop Range	Status
A	#739	North Reach	43	4-12	done
B	#740	South Reach	47	4-10	done
C	#741	East Reach	47	4-9	done
D	#742	West Reach	50	4-17	done
E	#743	All corridors (remainder)	120	4-23	hops 4-7 done (65 systems); 55 remaining

Use tooling/atlas next {hop} to get the system list per hop. Use tooling/atlas unfinished to see all remaining systems.

PR Strategy

One PR per corridor track, all from copy branch.

Quality Standards (from hops 0-3)

• Body count: G/F stars 8+, K stars 7+, M dwarfs 6+, A/B stars 6+
• Always include: oort cloud, asteroid belt, gas giant (most systems), horizon station
• Names: Inhabited bodies + all stations get proper_name. Uninhabited bodies = null. Wiki names override Miri.
• Population: Hub 1-5B, junction 500M-2B, loop/through 200M-1B, dead end 10M-500M. Adjust for wave + role.
• No translations in notes — translations flatten names into labels
• One commit per system — never batch

Tickets

• Epic #738: Body catalog completion (parent: #746 Phase 1)
• Story #739: Track A — North Reach
• Story #740: Track B — South Reach
• Story #741: Track C — East Reach
• Story #742: Track D — West Reach
• Story #743: Track E — Deep Frontier

Key References

• .claude/skills/atlas/references/ — all pipeline subfiles
• docs/design/cultural-migration-pressure.md — corridor cultural framework
• docs/atlas/corridor-assignments.md — parallel work structure
• wiki/corporations/index.md — corporate entities for industrial_corridor tags