claudemd-cli 0.96.0 → 0.97.0

package/README.md

@@ -1,12 +1,12 @@
 # claudemd
 
-> A **personal AI-coding discipline harness**: one developer's opinionated **AI-CODING-SPEC v6.33**, 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 v6.34**, 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 v6.33 — 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 v6.34 — 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 &
 | 22 shell hooks | `banned-vocab-check` · `pre-bash-safety-check` · `ship-baseline-check` · `residue-audit` · `memory-read-check` · `memory-prompt-hint` · `sandbox-disposal-check` · `session-start-check` · `session-extended-read` · `session-summary` · `session-end-check` · `transcript-vocab-scan` · `rework-breaker` · `cross-repo-write-check` · `tmp-sweep` · `branch-prune` · `evidence-gate` · `ledger-staleness` · `reply-language-check` · `transcript-structure-scan` · `version-sync` · `mem-audit` |
 | 16 slash commands | `/claudemd-install` · `/claudemd-status` · `/claudemd-update` · `/claudemd-refresh` · `/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 v6.33 | `~/.claude/CLAUDE.md` · `CLAUDE-extended.md` · `CLAUDE-changelog.md` · `OPERATOR.md` (backup-before-overwrite) |
+| Spec v6.34 | `~/.claude/CLAUDE.md` · `CLAUDE-extended.md` · `CLAUDE-changelog.md` · `OPERATOR.md` (backup-before-overwrite) |
 | StatusLine (opt-out) | PS1-style line — `user@host:dir (branch) Model [ctx:N% · 5h:N% · 7d:N%]` (`dir` = cwd basename; 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 backs up a hand-written `~/.claude/CLAUDE.md` (any file without the `# AI-CODING-SPEC` H1) to `~/.claude/backup-<ISO>/` before overwriting (last 5 kept automatically). An already-installed claudemd spec never enters `backup-<ISO>/` — deliberate (v0.23.11): no directory in that namespace ever has the spec as its `CLAUDE.md`, so `restore` can never return a stale spec instead. (The user-content sweep does move `CLAUDE-extended.md`, `CLAUDE-changelog.md` and `OPERATOR.md` along beside your own file, so the directory is not literally yours alone — the `CLAUDE.md` in it is.) It is not discarded either (v0.83.0): unless it already matches the shipped spec byte for byte, it is copied to `spec-backup-<ISO>/`, a separate namespace `restore` does not read (last 5 kept). Uninstall offers `keep / restore / delete`; `delete` requires an extra confirmation.
@@ -80,7 +80,7 @@ Once installed, hooks run silently in the background. Verbose log: `~/.claude/lo
 | `git push` while the pushed branch's CI is red | `ship-baseline-check` | Blocks the push (2-second `gh run list` timeout; fail-open if `gh` absent or times out). |
 | Bash command matching ship/push/deploy/release with an unread matched `MEMORY.md` entry | `memory-read-check` | Blocks the command with a list of memory files to Read first. |
 | Session end with `~/.claude/tmp/` growth > 20 entries | `residue-audit` | Advisory stderr warning; never blocks. |
-| Session end with fresh `tmp.XXXXXX`-style directories | `sandbox-disposal-check` | Advisory stderr warning. |
+| Session stop with fresh test/probe residue: `tmp.XXXXXX` / `claudemd-*` directories in `~/.claude/tmp` or `/var/tmp`, `claudemd-*` in `/tmp`, or a `~/.claude/projects/` dir left by a headless `claude -p` run from a temp cwd (the session's own transcript dir excluded); judged since the session's previous Stop, by mtime, so a concurrent session's sandbox can show up | `sandbox-disposal-check` | Advisory stderr warning by default. Opt-in `SANDBOX_DISPOSAL_BLOCK=1` (v0.97.0+, default OFF) returns `{"decision":"block"}` naming up to five, with a reason that some may belong to another session, so the session removes the ones it created before finishing, once per turn (`stop_hook_active`). |
 | Session end (Stop), at most once per 24h | `mem-audit` (v0.9.4+) | Scans CC auto-memory `~/.claude/projects/*/memory/feedback_*.md` for missing `**Why:**` / `**How to apply:**` body structure plus MEMORY.md ↔ files index drift; advisory stderr, never blocks. |
 | Session end | `session-summary` (v0.8.0+) | Writes `~/.claude/.claudemd-state/last-session-summary.json`; banner emit at next `SessionStart`. |
 | New session start with GitHub remote tag newer than local cache max version | `session-start-check` (v0.4.0+) | Injects an "upgrade available" banner via `additionalContext`. Rate-limited to once per 24h via `~/.claude/.claudemd-state/upstream-check.lastrun` sentinel. 3-second `git ls-remote` timeout, fail-open. |
@@ -89,7 +89,7 @@ Once installed, hooks run silently in the background. Verbose log: `~/.claude/lo
 | First `UserPromptSubmit` after a mid-session `/plugin install` upgrade | `version-sync` (v0.3.1+) | Backgrounds `install.js` once per session when the manifest version diverges from the active plugin's `package.json`. Sentinel-gated; fail-open. |
 | Session stop with a completion claim in the last assistant message and no verification output behind it | `evidence-gate` (v0.90.0+) | Stop advisory — judges the TRANSCRIPT (is there a non-error Bash result after the last code edit whose command names a runner, or whose output looks like one) rather than the prose, which is what the prose-reading detector closed in the 2026-07-24 labeling pass, one of six closed there at a pooled precision bound of 0.17 were doing. Opt-in (`EVIDENCE_GATE=1`, default OFF) for FP signal collection. |
 | Session stop after code edits, with a long-task ledger under `cwd` that nothing wrote to | `ledger-staleness` (v0.91.0+) | Stop advisory — the third G7 arm, beside the `SessionStart` re-injection. Both halves are transcript structure over the same tail window: a code-file `Edit`/`Write` in it, and no `Edit`/`Write` on the resolved `tasks/<slug>-ledger.md` in it. The window is a staleness threshold rather than a scanning budget, so a ledger written more than a window ago reads as behind. No ledger means the convention is not in use in this project; a ledger older than `CLAUDEMD_LEDGER_MAX_AGE_DAYS` (default 14) means a finished task. Either way it stays silent — and the age bound is skipped rather than guessed if `hooks/lib/platform.sh` is unavailable, so on that path an old ledger can still draw the advisory. Opt-in (`LEDGER_STALENESS=1`, default OFF) for FP signal collection. |
-| Session stop whose last reply is English while the human writes 中文 | `reply-language-check` (v0.96.0+) | Stop, the one claudemd hook that returns `{"decision":"block"}`: the turn continues for one more message, asking for the same content in 中文 (no new work, no tools); the English text already shown stays. The human's language comes from the human's own messages only — task notifications, teammate messages, meta rows and tool results never count; a slash command counts by its arguments; a message typed mid-turn counts. The majority language of the human's newest 20 messages decides, so one pasted English log does not flip a 中文 session. What the human says about language is not parsed: a 中文 request for English replies, a translation or an `英文版` still gets a 中文 restatement — turn the hook off or set it to `log` for that. A reply whose first line is a conventional-commit subject is not judged. Headless `claude -p` runs are skipped, and it asks at most once per turn (`stop_hook_active`). Opt-in: `REPLY_LANGUAGE_CHECK=1`, or `=log` to record without asking; default OFF. |
+| Session stop whose last reply is English while the human writes 中文 | `reply-language-check` (v0.96.0+) | Stop, returning `{"decision":"block"}` (as `sandbox-disposal-check` does under its opt-in): the turn continues for one more message, asking for the same content in 中文 (no new work, no tools); the English text already shown stays. The human's language comes from the human's own messages only — task notifications, teammate messages, meta rows and tool results never count; a slash command counts by its arguments; a message typed mid-turn counts. The majority language of the human's newest 20 messages decides, so one pasted English log does not flip a 中文 session. What the human says about language is not parsed: a 中文 request for English replies, a translation or an `英文版` still gets a 中文 restatement — turn the hook off or set it to `log` for that. A reply whose first line is a conventional-commit subject is not judged. Headless `claude -p` runs are skipped, and it asks at most once per turn (`stop_hook_active`). Opt-in: `REPLY_LANGUAGE_CHECK=1`, or `=log` to record without asking; default OFF. |
 | `PostToolUse` on `Edit`/`Write`, at each 8th edit of one file in one session | `rework-breaker` (v0.90.0+) | Advisory; injects one line naming the count (§1 Root cause over patch). Opt-in (`REWORK_BREAKER=1`, default OFF) for FP signal collection — a large legitimate refactor looks identical from here. |
 | `PreToolUse` on `Edit`/`Write`/`NotebookEdit`/`Bash`, when the target is a git repo other than the session's project | `cross-repo-write-check` (v0.95.0+) | Advisory, never a verdict; injects one line per target repo per session: stop and ask unless the user asked for that repo, and use `git worktree add` rather than switching branches in its shared tree. Bash side sees git writes after a literal `cd` or `git -C` only. Opt-in (`CROSS_REPO_WRITE=1`, default OFF); `CROSS_REPO_WRITE_ALLOW` takes colon-separated absolute repo roots (a leading `~/` or `$HOME/` is expanded). |
 | `PostToolUse` on any `Bash` call, at most once per 10 min | `tmp-sweep` (v0.93.0+) | Deletes, detached, the per-run dirs vitest leaves in the temp root and never removes (`<tmp>/<21-char id>/ssr/<sha1>`, 13-45 MB each; on a tmpfs `/tmp` that is RAM). Only the exact vitest signature, only when idle 60 min (24 h while a vitest watcher runs), across `$TMPDIR`, `/tmp` and `~/.cache/tmp`. Also injects one line when the temp root (`$TMPDIR`, else `/tmp`) is ≥ 80% full. Parallel Bash calls claim the slot atomically, so one sweep runs (a few can overlap only while a lock left by a killed hook is being cleared). **On by default.** |
@@ -189,7 +189,7 @@ export DISABLE_SHIP_BASELINE_HOOK=1              # or
 export DISABLE_RESIDUE_AUDIT_HOOK=1              # or
 export DISABLE_MEMORY_READ_HOOK=1                # or
 export DISABLE_MEMORY_HINT_HOOK=1                # v0.11.0+ — UserPromptSubmit MEMORY.md tag pre-matcher (proactive §11 hint)
-export DISABLE_SANDBOX_DISPOSAL_HOOK=1           # or
+export DISABLE_SANDBOX_DISPOSAL_HOOK=1           # Stop §8.V4 residue scan (opt-in block: SANDBOX_DISPOSAL_BLOCK=1, v0.97.0+)
 export DISABLE_SESSION_START_HOOK=1              # or
 export DISABLE_SESSION_SUMMARY_HOOK=1            # v0.8.0+ — Stop hook writing summary
 export DISABLE_USER_PROMPT_SUBMIT_HOOK=1         # version-sync (mid-session upgrade re-install)
@@ -433,7 +433,7 @@ claudemd/
 ├── commands/                 # 16 slash-command markdown files
 ├── bin/                      # standalone CLI entrypoint (claudemd-lint.js → `npx claudemd-cli` on npmjs.org)
 ├── scripts/                  # 20 Node.js scripts + scripts/lib/ (single-source registry, lint, etc.)
-├── spec/                     # shipped v6.33 CLAUDE*.md trio + OPERATOR.md + hard-rules.json manifest
+├── spec/                     # shipped v6.34 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 20/22/24) + npm-publish.yml (tag-triggered)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudemd-cli",
-  "version": "0.96.0",
+  "version": "0.97.0",
   "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": {