chore(voyage): release v5.7.1 - relocate agent example blocks (always-loaded token trim)

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "voyage",
   "description": "Voyage — brief, research, plan, execute, review, continue. Contract-driven Claude Code pipeline. /trekbrief, /trekplan, and /trekreview each end by building a self-contained operator-annotation HTML (scripts/annotate.mjs, modelled on claude-code-100x): select text or click any element, pick intent (Fiks/Endre/Spørsmål), write comment, copy structured prompt, paste back, Claude revises the .md.",
-  "version": "5.7.0",
+  "version": "5.7.1",
   "author": {
     "name": "Kjell Tore Guttormsen"
   },

CHANGELOG.md

@@ -4,6 +4,18 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
+## v5.7.1 — 2026-06-29 — relocate agent `<example>` blocks to body (always-loaded token trim)
+
+Performance/packaging change — no behavior change, no breaking change. (M4)
+
+### Always-loaded token trim
+
+- The 17 example-bearing agents each carried two `<example>` blocks (34 total) inside their `description:` frontmatter. voyage launches its agents **by name** from the orchestrator commands, so those auto-selection examples were paying a per-turn token tax for a path the pipeline never uses. They are now relocated **verbatim** into each agent's body under a `## When to use — examples` section — preserved, not deleted.
+- Frontmatter `description` chars across all 24 agents: **17,672 → 4,945** — roughly **3,180 fewer always-loaded tokens per turn** for every session with voyage enabled. The 7 zero-example agents are untouched; no system prompt, tools, model, or `name` changed.
+- New invariant test in `tests/lib/agent-frontmatter.test.mjs`: no `<example>` in any frontmatter `description`, and ≥ 34 `<example>` retained across agent bodies (relocation moves, never deletes). Suite: **807 pass / 0 fail / 2 skip**.
+- **The saving only reaches a machine after `/plugin marketplace update` + reload** — the delta is not instant on the machine that ships the release.
+- Version sync: `plugin.json`, `package.json`, `package-lock.json`, README badge, CHANGELOG top entry all at `5.7.1`, guarded by `doc-consistency.test.mjs`.
+
 ## v5.7.0 — 2026-06-26 — opt-in token/cost metering (SKAL-2) + eval foundation (SKAL-1·4a)
 
 Additive — no breaking change. Two unreleased work-streams land together.

README.md

@@ -1,6 +1,6 @@
 # trekplan — Brief, Research, Plan, Execute, Review, Continue
 
-![Version](https://img.shields.io/badge/version-5.7.0-blue)
+![Version](https://img.shields.io/badge/version-5.7.1-blue)
 ![License](https://img.shields.io/badge/license-MIT-green)
 ![Platform](https://img.shields.io/badge/platform-Claude%20Code-purple)
 
@@ -10,7 +10,7 @@
 
 A [Claude Code](https://docs.anthropic.com/en/docs/claude-code) plugin for deep implementation planning, multi-source research, autonomous execution, independent post-hoc review, and zero-friction multi-session resumption. Six commands, one pipeline:
 
-> **What's new — v5.6.1: leaner always-loaded agent listing.** The four reference/dormant agents (the three `*-orchestrator` reference docs + the dormant `synthesis-agent`) now carry one-line `description:` frontmatter — their full rationale already lives in each file's body — trimming ~700 tokens from the agent listing injected into every session, with no behavior change. **v5.6.0: `/trekexecute` loop hardening.** Execution-loop termination is now machine-verifiable (completion gate, Hard Rule 18) and recovery is bounded by an explicit `TREKEXECUTE_MAX_RECOVERY_ITERATIONS` budget (default 25, Hard Rule 20). The prior coordinated release **v5.5.0** added brief **framing** enforcement (`brief_version 2.2`) + a `/trekreview` reviewer-schema contract. Additive — no breaking changes. **Full version history → [CHANGELOG.md](CHANGELOG.md).**
+> **What's new — v5.7.1: leaner always-loaded agent listing (round 2).** The 17 example-bearing agents now keep their `<example>` blocks in the body (under `## When to use — examples`) instead of the `description:` frontmatter — voyage launches its agents by name, so the auto-selection examples were cost without function there. This trims ~3,180 always-loaded tokens (frontmatter `description` chars 17,672 → 4,945) from the agent listing injected into every session, with no behavior change. The saving lands after `/plugin marketplace update` + reload. **v5.7.0:** opt-in per-session token/cost metering (SKAL-2) + eval foundation (SKAL-1·4a). **v5.6.1:** one-line `description:` for the four reference/dormant agents (~700 tok). **v5.5.0:** brief **framing** enforcement (`brief_version 2.2`) + a `/trekreview` reviewer-schema contract. Additive — no breaking changes. **Full version history → [CHANGELOG.md](CHANGELOG.md).**
 
 | Command | What it does |
 |---------|-------------|

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "voyage",
-  "version": "5.7.0",
+  "version": "5.7.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "voyage",
-      "version": "5.7.0",
+      "version": "5.7.1",
       "license": "MIT",
       "engines": {
         "node": ">=18"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "voyage",
-  "version": "5.7.0",
+  "version": "5.7.1",
   "description": "Voyage — brief, research, plan, execute, review, continue. Contract-driven Claude Code pipeline. /trekbrief, /trekplan, and /trekreview each end by building a self-contained operator-annotation HTML (scripts/annotate.mjs, modelled on claude-code-100x): select text or click any heading/paragraph/list-item, pick intent (Fiks/Endre/Spørsmål), write comment, copy structured prompt, paste back, Claude revises the .md.",
   "type": "module",
   "engines": {