claudemd-cli 0.31.0 → 0.32.1

package/CHANGELOG.md

@@ -8,6 +8,21 @@ All notable changes to the `claudemd` plugin. This changelog tracks plugin artif
 - **Canonical spec version source**: `spec/CLAUDE.md` top-line title (`# AI-CODING-SPEC vX.Y.Z — Core`) + `spec/CLAUDE-changelog.md` top `##` entry.
 - **Plugin semver vs spec semver** are independent: plugin patch (0.2.0 → 0.2.1) may ship when spec is unchanged (this release); plugin minor (0.1.9 → 0.2.0) ships when spec minor updates (v0.2.0 shipped spec v6.10.0).
 
+## [0.32.1] - 2026-07-10
+
+**Patch — statusline: ctx segment no longer disappears right after `/clear`.** Reported live: immediately after `/clear` the meter rendered `[5h:0% · 7d:52%]` with no ctx segment. Root cause (verified against the CC 2.1.206 binary's payload constructor): before the first API response of a fresh session, CC sends `context_window` with an **explicit `used_percentage: null`** ("no usage yet"), which the renderer treated as "no data" and omitted. The `5h:0%` in the report was real data (new 5-hour window, fractional utilization floored), not part of the bug.
+
+- **Fix** (`scripts/statusline.sh`): ctx extraction now distinguishes explicit-null from absent — `context_window` object present with a `used_percentage` key → null renders as `ctx:0%`; missing key / missing object / non-object still hides the segment (no fabricated 0% on foreign or pre-2.1.206 payloads). Side hardening: a non-object `context_window` (e.g. a string) no longer errors the jq program mid-stream.
+- **Tests**: `tests/scripts/statusline.test.js` 20 → 23 cases (byte-shape post-/clear fixture with explicit nulls, object-without-key hidden, non-object garbage keeps later fields aligned).
+- **Action on upgrade**: re-run `/claudemd-statusline` or any install/update to refresh `~/.claude/claudemd-statusline.sh`.
+
+## [0.32.0] - 2026-07-10
+
+**Minor — spec v6.15.0: §2.1 Model tiering (spawned-agent model selection).** Core §2.1 gains a SHOULD-level block after Tool escalation: spawned agents default to inheriting the session model (omit `model` when unsure); whitelist downgrade — sonnet for mechanical fan-out (search / fetch / extract / classify / enumerate) + lint-or-test-gated bulk edits, opus for test-gated plan-step code; decision-shaped stages (orchestrate / synthesize / verify / judge / root-cause debug / L3 / §5-hard / §8) NEVER downgrade. Invariants: verifier tier ≥ generator; anomalous downgraded output → one re-run at inherited tier; evidence bar tier-independent. Paired net-delete: §7 metric-coupled row's 6 project-specific examples removed (Candidate 1 of `tasks/core-net-delete-candidates-v6.14.md`, −169B measured vs −280~340 estimated). Core lands at 24978/25000 (22B headroom — next core addition must fully net-delete). Design doc: `tasks/specs/model-tiering.md`.
+
+- **No hook / script changes** — spec text + version cascade only. `hard-rules.json` rules array unchanged (spec_version field bump only; rule is SHOULD, not HARD, per §13.2 budget gates).
+- Version cascade: spec headers ×2, `spec/hard-rules.json` spec_version, `tests/scripts/spec-structure.test.js` (2 asserts), `tests/integration/upgrade-lifecycle.test.sh` NEW_SPEC_VER, manifest descriptions v6.14 → v6.15 per v0.2.1 policy.
+
 ## [0.31.0] - 2026-07-10
 
 **Minor — statusline 5h/7d quota segments (user-visible default change).** The shipped statusline renderer's meter bracket grows from `[ctx:N%]` to `[ctx:N% · 5h:N% · 7d:N%]` — context window plus the 5-hour and weekly rate-limit windows, all **used %** with uniform thresholds (<50 green, 50-79 yellow, >=80 red), rendered faint (SGR 2) so the meter doesn't pull attention. **Action on upgrade**: none — re-run `/claudemd-statusline` (or any install/update, which refreshes `~/.claude/claudemd-statusline.sh`) to pick up the new renderer. **Opt-out**: `DISABLE_STATUSLINE_QUOTA=1` hides the quota segments (exact-match `1`, matching the repo's toggle convention); full revert = pin v0.30.0 or `/claudemd-statusline remove`.

package/README.md

@@ -1,12 +1,12 @@
 # claudemd
 
-> A **personal AI-coding discipline harness**: one developer's opinionated **AI-CODING-SPEC v6.14**, encoded as Claude Code shell hooks and shipped with the plugin. Built and dogfooded on my own repos — fork and adapt, don't adopt wholesale.
+> A **personal AI-coding discipline harness**: one developer's opinionated **AI-CODING-SPEC v6.15**, encoded as Claude Code shell hooks and shipped with the plugin. Built and dogfooded on my own repos — fork and adapt, don't adopt wholesale.
 
 [![CI](https://github.com/sdsrss/claudemd/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/sdsrss/claudemd/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/claudemd-cli.svg)](https://www.npmjs.com/package/claudemd-cli)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 
-claudemd plugs into the Claude Code hook system to **block commits, pushes, and bash commands** that violate AI-CODING-SPEC v6.14 — banned vocabulary in commit messages, `rm -rf $VAR` without variable validation, ship-on-red-CI, unread `MEMORY.md` entries during release flows, and more. The spec itself (`CLAUDE.md` + `CLAUDE-extended.md` + `CLAUDE-changelog.md` + `OPERATOR.md`) ships with the plugin and installs into `~/.claude/`, so the rules Claude Code reads at session start match the rules the hooks enforce. (`OPERATOR.md` is the human-only spec-maintenance handbook — Agent-loaded files are the CLAUDE trio.)
+claudemd plugs into the Claude Code hook system to **block commits, pushes, and bash commands** that violate AI-CODING-SPEC v6.15 — banned vocabulary in commit messages, `rm -rf $VAR` without variable validation, ship-on-red-CI, unread `MEMORY.md` entries during release flows, and more. The spec itself (`CLAUDE.md` + `CLAUDE-extended.md` + `CLAUDE-changelog.md` + `OPERATOR.md`) ships with the plugin and installs into `~/.claude/`, so the rules Claude Code reads at session start match the rules the hooks enforce. (`OPERATOR.md` is the human-only spec-maintenance handbook — Agent-loaded files are the CLAUDE trio.)
 
 A standalone CLI (`npx claudemd-cli`) reuses the same `banned-vocab.patterns` source for git pre-commit hooks, GitHub Actions, and other agents that don't run inside Claude Code.
 
@@ -60,7 +60,7 @@ Verify in one command (Linux): `node --version && jq --version && gh --version &
 | 16 shell hooks | `banned-vocab-check` · `pre-bash-safety-check` · `ship-baseline-check` · `residue-audit` · `memory-read-check` · `memory-prompt-hint` · `mid-spine-yield-scan` · `sandbox-disposal-check` · `session-start-check` · `session-extended-read` · `session-summary` · `session-end-check` · `transcript-vocab-scan` · `transcript-structure-scan` · `version-sync` · `mem-audit` |
 | 15 slash commands | `/claudemd-install` · `/claudemd-status` · `/claudemd-update` · `/claudemd-audit` · `/claudemd-toggle` · `/claudemd-doctor` · `/claudemd-analyze` · `/claudemd-uninstall` · `/claudemd-rules` · `/claudemd-clean-residue` · `/claudemd-sparkline` · `/claudemd-sampling-audit` · `/claudemd-bypass-audit` · `/claudemd-design-adopt` · `/claudemd-statusline` |
 | 1 standalone CLI | `claudemd-cli lint` · `claudemd-cli audit` ([npm: `claudemd-cli`](https://www.npmjs.com/package/claudemd-cli)) |
-| Spec v6.14 | `~/.claude/CLAUDE.md` · `CLAUDE-extended.md` · `CLAUDE-changelog.md` · `OPERATOR.md` (backup-before-overwrite) |
+| Spec v6.15 | `~/.claude/CLAUDE.md` · `CLAUDE-extended.md` · `CLAUDE-changelog.md` · `OPERATOR.md` (backup-before-overwrite) |
 | StatusLine (opt-out) | PS1-style line — `user@host:/path (branch) Model [ctx:N% · 5h:N% · 7d:N%]` (context / 5-hour quota / weekly quota, all **used %**, read from Claude Code's `rate_limits` payload; quota segments auto-hide when the data is absent, or force-hide with `DISABLE_STATUSLINE_QUOTA=1`) — wired into `~/.claude/settings.json` on install **only when the slot is empty**; an existing statusline is left untouched. Skip entirely with `CLAUDEMD_NO_STATUSLINE=1`. Manage via `/claudemd-statusline`. |
 
 Install moves any existing `~/.claude/CLAUDE*.md` to `~/.claude/backup-<ISO>/` (last 5 kept automatically). Uninstall offers `keep / restore / delete`; `delete` requires an extra confirmation.
@@ -338,7 +338,7 @@ claudemd/
 ├── commands/                 # 12 slash-command markdown files
 ├── bin/                      # standalone CLI entrypoint (claudemd-lint.js → `npx claudemd-cli` on npmjs.org)
 ├── scripts/                  # 16 Node.js management scripts + scripts/lib/ (single-source registry, lint, etc.)
-├── spec/                     # shipped v6.14.2 CLAUDE*.md trio + OPERATOR.md + hard-rules.json manifest
+├── spec/                     # shipped v6.15.0 CLAUDE*.md trio + OPERATOR.md + hard-rules.json manifest
 ├── tests/                    # hook shell tests + Node.js tests + integration + fixtures
 ├── docs/                     # ADDING-NEW-HOOK.md + RULE-HITS-SCHEMA.md + superpowers/
 └── .github/workflows/        # ci.yml (ubuntu+macOS × node 20) + npm-publish.yml (tag-triggered)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudemd-cli",
-  "version": "0.31.0",
+  "version": "0.32.1",
   "description": "Standalone CLI for §10-V banned-vocab + transcript scanning. Companion to the claudemd Claude Code plugin (github.com/sdsrss/claudemd) for use in git pre-commit hooks, GitHub Actions, and other agents.",
   "type": "module",
   "bin": {