@su-record/vibe 4.1.11 → 4.1.12

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
-    "version": "4.1.11"
+    "version": "4.1.12"
   },
   "plugins": [
     {
       "name": "vibe",
       "source": "./",
       "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
-      "version": "4.1.11",
+      "version": "4.1.12",
       "category": "productivity"
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "vibe",
-  "version": "4.1.11",
+  "version": "4.1.12",
   "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
   "author": {
     "name": "su-record",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "vibe",
-  "version": "4.1.11",
+  "version": "4.1.12",
   "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
   "author": {
     "name": "su-record",

package/README.md

@@ -154,7 +154,7 @@ config.json      token policy · skill catalogs
 
 ## Status
 
-`4.0.0` — phase 1: CLI core + Claude Code. Phase 2: Codex CLI and ChatGPT desktop adapters, the work graph and typed ledger edges. Phase 3a: `http` / `eval` checks, column sums, sample profiling. Phase 3b: GitHub research, project-local skills and proposals. Phase 3c: the end-to-end order-settlement example. Phase 4: the bench and `ledger compare --by harness`. `4.0.2`: no `init` — the card, skills and hook live in the client home and any `vibe` command repairs them. `4.0.3`: `vibe uninstall` also clears what an older `init` left in the project. `4.1.0`: the package is the plugin — `npm i -g` registers a local plugin in Claude Code and Codex/ChatGPT, Hermes Agent joins as a client, `vibe plugin build --check` gates manifest drift. `4.1.1`: `vibe update`. `4.1.2`: the Claude desktop app through an MCP Bundle (`vibe plugin mcpb`). `4.1.3`: the bundle finds the CLI without the shell's PATH (Homebrew, nvm, fnm, volta) or from a path set at install. `4.1.4`: `vibe read` for xlsx · docx · pptx · pdf, `vibe profile` reads xlsx, card rule 8 (read files whole). `4.1.5`: `vibe read` for Hangul hwp · hwpx and html. `4.1.6`: `vibe size`, a built-in file/function size check for any project; the CLI split into modules; the repository's own limit is now per file (400), not a total. `4.1.7`: hook entries left by vibe 3 that point at a missing script are swept at every command, so Claude Code stops reporting them. `4.1.8`: the five stage skills are `vibe-discover` … `vibe-handoff` (a dot is outside the Agent Skills name grammar) and the dotted directories an older install left in a client home are swept; `.vibe/` means one thing — the plugin tree moves to `~/.config/vibe/plugin`, a `.vibe/` counts as a project only when it holds a record, the search stops at `.git` and never lands on the home, `vibe state` shows `root`, a `run` check that exits 127 names its cwd; the `review` check and the `antislop-ko` · `antislop-en` language packs — the harness runs a copy editor and a chief editor on human-read text and passes only on `PASS`. vibe 3 stays on its 3.x tags and is no longer developed. `4.1.9`: Codex follows `vibe update` — the version Codex actually holds is read from its cache, compared with the package and re-registered (remove + add) when behind; a marketplace entry still pointing at the ≤ 4.1.7 store is drift; `vibe status` reports the Codex plugin version it read, not the package version. `4.1.10`: `vibe read --ask` — the harness reads for the model: files (numbered) go to a low-reasoning reader on the client CLI and only the answer returns; the reader runs slim (own system prompt, no tools, no settings, neutral directory) and one session per file set is resumed for follow-up questions so the corpus is read from cache, with the hit reported; the hook advises `--ask` on reads over 400 lines; card rule 8 says when to delegate; the `review` check's Codex command gets `--skip-git-repo-check`. Also: `regress record` made ids longer than the 40-character rule, so every recorded regression was silently left out of `check --all` — the id now fits, a file that parses to nothing is named in `vibe state`, and the repository's four regressions run again. `4.1.11`: antislop reaches design — `antislop-design` and its two reviewers (markup reviewer, art director) join the text packs, reviewer stages are data (`reviewers/<pack>/N-<stage>.md`), the `review` check takes `pack`, a directory of source and a `screenshot`; the text packs gain strength tiers, five questions before a cut, the portability test, notes-to-the-writer, sample-outranks-rules and a what-is-not-a-tell list, and the reviewers may name what to keep.
+`4.0.0` — phase 1: CLI core + Claude Code. Phase 2: Codex CLI and ChatGPT desktop adapters, the work graph and typed ledger edges. Phase 3a: `http` / `eval` checks, column sums, sample profiling. Phase 3b: GitHub research, project-local skills and proposals. Phase 3c: the end-to-end order-settlement example. Phase 4: the bench and `ledger compare --by harness`. `4.0.2`: no `init` — the card, skills and hook live in the client home and any `vibe` command repairs them. `4.0.3`: `vibe uninstall` also clears what an older `init` left in the project. `4.1.0`: the package is the plugin — `npm i -g` registers a local plugin in Claude Code and Codex/ChatGPT, Hermes Agent joins as a client, `vibe plugin build --check` gates manifest drift. `4.1.1`: `vibe update`. `4.1.2`: the Claude desktop app through an MCP Bundle (`vibe plugin mcpb`). `4.1.3`: the bundle finds the CLI without the shell's PATH (Homebrew, nvm, fnm, volta) or from a path set at install. `4.1.4`: `vibe read` for xlsx · docx · pptx · pdf, `vibe profile` reads xlsx, card rule 8 (read files whole). `4.1.5`: `vibe read` for Hangul hwp · hwpx and html. `4.1.6`: `vibe size`, a built-in file/function size check for any project; the CLI split into modules; the repository's own limit is now per file (400), not a total. `4.1.7`: hook entries left by vibe 3 that point at a missing script are swept at every command, so Claude Code stops reporting them. `4.1.8`: the five stage skills are `vibe-discover` … `vibe-handoff` (a dot is outside the Agent Skills name grammar) and the dotted directories an older install left in a client home are swept; `.vibe/` means one thing — the plugin tree moves to `~/.config/vibe/plugin`, a `.vibe/` counts as a project only when it holds a record, the search stops at `.git` and never lands on the home, `vibe state` shows `root`, a `run` check that exits 127 names its cwd; the `review` check and the `antislop-ko` · `antislop-en` language packs — the harness runs a copy editor and a chief editor on human-read text and passes only on `PASS`. vibe 3 stays on its 3.x tags and is no longer developed. `4.1.9`: Codex follows `vibe update` — the version Codex actually holds is read from its cache, compared with the package and re-registered (remove + add) when behind; a marketplace entry still pointing at the ≤ 4.1.7 store is drift; `vibe status` reports the Codex plugin version it read, not the package version. `4.1.10`: `vibe read --ask` — the harness reads for the model: files (numbered) go to a low-reasoning reader on the client CLI and only the answer returns; the reader runs slim (own system prompt, no tools, no settings, neutral directory) and one session per file set is resumed for follow-up questions so the corpus is read from cache, with the hit reported; the hook advises `--ask` on reads over 400 lines; card rule 8 says when to delegate; the `review` check's Codex command gets `--skip-git-repo-check`. Also: `regress record` made ids longer than the 40-character rule, so every recorded regression was silently left out of `check --all` — the id now fits, a file that parses to nothing is named in `vibe state`, and the repository's four regressions run again. `4.1.11`: antislop reaches design — `antislop-design` and its two reviewers (markup reviewer, art director) join the text packs, reviewer stages are data (`reviewers/<pack>/N-<stage>.md`), the `review` check takes `pack`, a directory of source and a `screenshot`; the text packs gain strength tiers, five questions before a cut, the portability test, notes-to-the-writer, sample-outranks-rules and a what-is-not-a-tell list, and the reviewers may name what to keep. `4.1.12`: the agent's own report is not slop — card rule 9 (what changed apart from what `vibe check` verified; keep the caveat that changes the next step; an error is its cause and fix; answer first, no praise, apology or closing offer) and a Report voice section in `vibe-handoff` (each Built line names its check and run or says "not checked"; estimates in turns and tool calls, never calendar time; the handoff document follows `antislop-en`).
 
 ## Bench — the ledger is the benchmark
 

package/card.md

@@ -1,10 +1,11 @@
 You are working inside vibe. Rules:
 1. Before changing anything, run `vibe state --json` and continue from it.
-2. Nothing is done until `vibe check` says DONE. Never claim completion yourself.
-3. When the harness asks for a human token (approval or an irreversible action), show the number and wait for it in chat. Never invent one.
+2. Nothing is done until `vibe check` says DONE. Never claim it yourself.
+3. When the harness asks for a human token, show the number and wait in chat. Never invent one.
 4. If `vibe check` fails twice the same way, stop and `vibe ask`.
-5. Surface at most three things the user did not ask about, each with a reason from the harness.
-6. Record any failure you fixed with `vibe regress record`.
-7. Talk to the user in the user's language. Write every record (intent, scenarios, inbox, knowledge, docs) in English.
-8. Read files whole with your file reader; search only to find which file. To understand a file without editing or debugging it, `vibe read <files> --ask "…"`: a low-reasoning model reads, the answer returns with line numbers. Documents and samples: `vibe read` / `vibe profile`; images: your own eyes.
+5. Surface at most three unasked things, each with a harness reason.
+6. Record each fixed failure with `vibe regress record`.
+7. Talk in the user's language; write every record (intent, scenarios, inbox, knowledge, docs) in English.
+8. Read files whole; search only to find which file. A file you will not edit or debug: `vibe read <files> --ask "…"`. Documents, samples: `vibe read` / `vibe profile`; images: your eyes.
+9. Report what changed apart from what `vibe check` verified. Keep the caveat that changes the user's next step; cut other hedges. An error is its cause and its fix. Answer first; no praise, apology or closing offer.
 Start with `/vibe {request}`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@su-record/vibe",
-  "version": "4.1.11",
+  "version": "4.1.12",
   "description": "An AX/FDE harness for Claude Code, Codex CLI and ChatGPT desktop. Say what you need, approve the scenarios once; the harness proves the work by running the checks itself. Memory in plain files, human tokens for irreversible actions, a ledger instead of claims.",
   "type": "module",
   "bin": {

package/skills/vibe-handoff/SKILL.md

@@ -24,3 +24,15 @@ Done: {intent title}
 4. The commands in the handoff document must be proven to run (`run` check). If an approved scenario already covers the handoff check, run `vibe check` on it. If not, ask the user whether to add a handoff scenario and re-approve.
 5. A final irreversible action (deploy, send) follows the token procedure in `vibe-build` exactly.
 6. If something should be kept for the next request (a repeated question, a customer convention), propose `vibe knowledge add`.
+
+## Report voice
+
+The completion report and the handoff document follow card rule 9. The verdict is `vibe check`'s line, never yours.
+
+- Each "Built" line says what changed and names the check and run that verified it (`tests [run] r-3`), or says "not checked".
+- "successfully", "should work" and "everything is in place" never appear. Say what ran and what it returned.
+- Keep the caveat that changes the operator's next decision: scope, risk, what was left out and why. Cut every other hedge.
+- An error is its cause, then its fix. No apology, no "uh oh", no closure the checks did not give.
+- The command or the answer leads; explanation follows only where it is needed.
+- Estimate remaining work in your own units: turns and tool calls, plus the one variable that widens the range (a build, a test suite, a review). Never human calendar time.
+- The handoff document is human-read English: `antislop-en` applies to it. When the intent has room, propose a `review` scenario on it (`⚠ model-judged`).