docs(claude-md): trim CLAUDE.md to invariants (always-loaded token trim, S53)

Relocate the verbose rationale/history from six always-loaded block-quote
notes (L5/L7/L9/L11/L56/L58) to the docs that already own it, leaving a terse
invariant + pointer in each. No invariant fact deleted — moved.

  L5  synthesis-PoC Δ≈0 caveat   → kept one clause; detail in T1-synthesis-poc-results.md
  L7  v3.0.0 architect note      → CHANGELOG.md [3.0.0]
  L9  Trinity Tier 2/3 detail    → HANDOVER-CONTRACTS.md §Handover 1 (added the producer-context para)
  L11 brief-framing 3-layer gate → HANDOVER-CONTRACTS.md §Handover 1 (already owned)
  L56 sonnet-downgrade rationale → voyage-vs-cc-balance-analysis.md §10 (D3)
  L58 per-agent effort table     → profiles.md §Model & effort axes

Measured (config-audit manifest scanner): voyage project CLAUDE.md
2261 → 1759 always-loaded tok (-502, -22%). Tables (Commands/Agents) left
byte-exact; doc-consistency pins (parallel wall-clock, 21 spawnable,
3 orchestrator reference docs, synthesis-agent dormant) preserved.

Docs-only: no version bump, no catalog ref. Suite 809 (807/0/2) green;
doc-consistency 87/0. Also tracks the task brief (provenance).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RZHLfnJXGx55G4euxPuxim

docs/HANDOVER-CONTRACTS.md

@@ -45,6 +45,8 @@ Every validator exposes a CLI: `node lib/validators/<name>.mjs --json <path>` re
 
 **Stability tier: PUBLIC CONTRACT.** Handover 1 is the *only* public integration boundary of the pipeline: `brief.md` is what an upstream producer hands to Voyage, and Voyage consumes it without any knowledge of who produced it. This asymmetry is a hard invariant (see `CLAUDE.md` §Trinity context) — the interactive `/trekbrief` interview is just one producer; a `manual` brief, or an external per-app / per-portfolio producer, is equally valid as long as the artifact conforms to the schema below. No producer is privileged. The consequence: changing this schema — renaming or removing a field, narrowing an enum, or promoting an optional field to required — is a **breaking change for every downstream consumer** and MUST follow the [breaking-change protocol](#breaking-change-protocol) (version bump + N-1 compatibility window). Additive *optional* fields are non-breaking by design: the validator tolerates unknown frontmatter keys silently (forward-compat), so a newer brief still validates against an older consumer. The v5.5.0 contract formalization established `brief_version` **2.1** as the public-contract baseline and, in the same coordinated release, **evolved it to `2.2`** under the breaking-change protocol — adding the required `framing` field + `## TL;DR` section gated at ≥ 2.2 (existing 2.0/2.1 briefs stay valid). See the Versioning paragraph below for the 2.2 details.
 
+**Trinity producer context (informational).** In the author's private three-tier design, Voyage is **Tier 1** (per-task). Its upstream producers are **Tier 2 `app-creator`** (per-app — "what does the app need, what's the next brief?") and **Tier 3 `app-factory`** (per-portfolio — "which app needs me now?"), both pre-implementation and bound for Forgejo when ready. None is privileged: any schema-conforming producer is equally valid, and Voyage stays unaware of Tier 2/3 — this Handover is the only coupling.
+
 **Producer:** `/trekbrief` Phase 4g (after `brief-reviewer` stop-gate passes or iteration cap is hit).
 
 **Consumer:** `/trekresearch` Phase 1 (mode parse + brief validation).

docs/claudemd-token-trim-brief.md

@@ -0,0 +1,40 @@
+# Brief — trim voyage CLAUDE.md to invariants (always-loaded token reduction)
+
+**Author:** config-audit machine-tuning loop (KTG). **Date:** 2026-06-29.
+**Why config-audit didn't do this directly:** voyage is the operator's plugin — config-audit only writes briefs here, never code. Run this in a voyage session.
+
+## Goal
+
+`CLAUDE.md` is injected **every turn** while working in the voyage repo (the whole per-repo always-loaded delta). Measured with config-audit `manifest`: **2,261 always-loaded tokens**. The tables (commands, agents) are invariant; the cost sits in six design-history / context **block-quote notes** whose detail already lives in referenced docs. Moving them out (leaving a terse invariant + pointer) should cut **~900–1,200 tok (~40–50 %)** with zero capability loss.
+
+## Hard constraints (do NOT break these)
+
+- `tests/lib/doc-consistency.test.mjs` reads CLAUDE.md. Keep the **Commands table** and the **Agents table including the `Model` column** and any **count** the test cross-checks. After editing, `node --test 'tests/**/*.test.mjs'` and `bash verify.sh` must stay green.
+- Keep every **invariant fact** — just relocate the verbose *rationale/history* to the doc that already owns it, and leave a one-line pointer. Don't delete facts; move them.
+- Docs-only change → no version bump / no catalog ref unless the doc-consistency test demands a badge sync (it shouldn't for a CLAUDE.md prose trim).
+
+## Trim targets (line numbers as of commit at brief time; match by content)
+
+| Block | ~chars / ~tok | Action | Destination (already referenced) |
+|-------|---------------|--------|----------------------------------|
+| L5 design-principle parenthetical (synthesis-PoC Δ≈0 caveat) | 620 / ~155 | **Keep the honesty caveat in one short clause** ("main-context relief is asserted-by-design, not measured — see doc"), move the PoC explanation out | `docs/T1-synthesis-poc-results.md` |
+| L7 v3.0.0 architect-extraction note | 376 / ~94 | Replace with a one-liner: the plan command auto-discovers `architecture/overview.md` if present (migration history → CHANGELOG) | `CHANGELOG.md` |
+| L9 Trinity context (Tier 1/2/3) | 859 / ~215 | Keep the **asymmetry invariant** terse ("Voyage stays unaware of Tier 2/3; Handover 1 = the only integration point; brief-schema changes are breaking"), move the Tier 2/3 description out | `docs/HANDOVER-CONTRACTS.md` §Handover 1 |
+| **L11 brief-framing 3-layer gate** | **1,585 / ~396** | Biggest. Keep one invariant line ("brief framing must match operator intent — enforced as the `brief_version 2.2` gate: `framing` frontmatter + memory-alignment dim 6 + `## TL;DR`; all BLOCKER for ≥2.2"), move the implementation detail out | `docs/HANDOVER-CONTRACTS.md` §Handover 1 (PUBLIC CONTRACT) |
+| L56 S33 agent-inventory reconcile | 740 / ~185 | Keep the terse fact ("24 agent files = 21 spawnable + 3 orchestrator reference docs; `synthesis-agent` dormant; all `opus`"), move the sonnet-downgrade rationale out | `docs/voyage-vs-cc-balance-analysis.md` §10 |
+| L58 Model & effort axes | 588 / ~147 | Keep one line ("`opus`=Opus 4.8 / `high`; select agents carry native `effort:`; distinct from brief `phase_signals.effort`"), move the per-agent effort table + axes explanation out | `docs/profiles.md` §Model & effort axes |
+
+**Net:** ~2,261 → ~1,300 tok. (Verify the after-figure with `node /path/to/config-audit/scanners/manifest.mjs <voyage-path>` → the `project` `claude-md` source.)
+
+## Procedure
+
+1. For each block above, confirm the destination doc already contains the detail (it's referenced, so it should) — if not, move the prose there first.
+2. Replace each block-quote with its terse invariant + pointer.
+3. Leave Commands/Agents tables byte-exact (counts + model column).
+4. `node --test 'tests/**/*.test.mjs'` + `bash verify.sh` green; confirm `doc-consistency` passes.
+5. Re-measure; commit `docs(claude-md): trim CLAUDE.md to invariants` to voyage's Forgejo. Δ lands on the machine after operator `/exit` + reload.
+
+## Notes
+
+- This mirrors the same trim already done directly in config-audit (−662 tok), linkedin-studio (−2,266), ms-ai-architect (−346), okr (−15), portfolio-optimiser (−93) — same principle: CLAUDE.md carries invariants for working on the plugin; history/rationale lives in CHANGELOG + docs/.
+- The voyage honesty culture (no overclaiming) is *preserved*, not trimmed: the synthesis-PoC Δ≈0 caveat stays as a one-liner; only the long-form explanation moves to its doc.