@dzhechkov/harness-cli 0.5.0 → 0.5.1

package/.dz-manifest.json

@@ -9,7 +9,7 @@
       },
       {
         "path": "README.md",
-        "sha256": "27e2ddfd256e5c89a1c51a2520b52cc4b947dd7295f5730bde0a2c735186fb8f"
+        "sha256": "6d4e868f0fef3d86f83c6316f4bb760fd9228ef1008d3bbb31916f6c8890b944"
       },
       {
         "path": "coverage/coverage-final.json",
@@ -37,23 +37,23 @@
       },
       {
         "path": "dist/cli.d.ts",
-        "sha256": "56db11f99b505b2ffbc314aa70b4bcd17ec741e14ca99a3662d0ca9f4afcc1cc"
+        "sha256": "3893831e365016b5bd118f7f0ce2e8b106cfd0400689b9e190a5f80aa61b79f5"
       },
       {
         "path": "dist/cli.d.ts.map",
-        "sha256": "19170be889713fffd051dfde1044074125f66bb4623e415c355f812a47721436"
+        "sha256": "514bbdd5b14a1257693418c64bf2fb6c13d78beccd307f0f3a9c66461a42a62f"
       },
       {
         "path": "dist/cli.js",
-        "sha256": "c80fe1740887b68a3521ee6d22e09303785238c6e27dd0c80fb76289927e73a4"
+        "sha256": "09277bf170699a591ca9d2c8f6ac3b2727ec41cff3a75e56058724bd1e4686e1"
       },
       {
         "path": "dist/cli.js.map",
-        "sha256": "1ef2072181086e6b14c30005417f3edba91db5c3f2ae82201236ea493385d6a8"
+        "sha256": "e2a46281a86931f342cf726ae0fd0aeb25eef7ce94edbd07abce68635f547e78"
       },
       {
         "path": "dist/core-compat.d.ts",
-        "sha256": "dedfc859e163f229af0445d6439172a4b66c150c0942bce3ae1bf0304dbb3290"
+        "sha256": "868dd0e0ec12ea9df5f4df148518f5c59226ecc1de04fa67d5455f4932a7819b"
       },
       {
         "path": "dist/core-compat.d.ts.map",
@@ -61,7 +61,7 @@
       },
       {
         "path": "dist/core-compat.js",
-        "sha256": "57930e6918c2a5d90826c74924a62de9a1ffab53d8196ff8f98a59c89baf23be"
+        "sha256": "973e9bd7c0951e9f74bd3e8b38a0cc81076d6ea8393fa3e52a428b92ebc967c8"
       },
       {
         "path": "dist/core-compat.js.map",
@@ -69,19 +69,19 @@
       },
       {
         "path": "dist/index.d.ts",
-        "sha256": "aaac0134a074fd06e9b5e09daa952ef6353510e481885da51a6e4f2e92beba35"
+        "sha256": "a25d0a97a30fa5abc35473ed4ca1bc32bc5a8bcb8a45c57d7feeb03cb6058e02"
       },
       {
         "path": "dist/index.d.ts.map",
-        "sha256": "459c3381a9fbcd3378b623f9fe103a8d3337e4025a2f546b6d40e4d9dd4e0f70"
+        "sha256": "7c554d109fb0aabcf9a2923b0d9ac84723652abdec81202b2cc0a726d38c84bd"
       },
       {
         "path": "dist/index.js",
-        "sha256": "15ff1e6b84537b91b73b6a7e2d1c45f1120b25af9d1139df8da8ad094e99cf0e"
+        "sha256": "5b7992e09b843a01c9bf7a05b5db4475ca9abbf893ead79f7bad73f0f92c4249"
       },
       {
         "path": "dist/index.js.map",
-        "sha256": "2f61a3be1af4ab9f7bbcbacb912ccbd89e3b73414f9fd24766598bfbdc1f8655"
+        "sha256": "54c8133a172c2ca81c3f5a32e701386812a621198758423fcc7f0bf3db8c1ff7"
       },
       {
         "path": "keys/README.md",
@@ -89,7 +89,7 @@
       },
       {
         "path": "package.json",
-        "sha256": "be73e142cc0dcd05cf774c73827572b1e55e503c8ab84f4a396fa785b271980b"
+        "sha256": "503d43d8ab6e7fb04c28f96270eb00da9782e4ec0570772f2f701aef33037c25"
       },
       {
         "path": "src/bin.ts",
@@ -97,15 +97,15 @@
       },
       {
         "path": "src/cli.ts",
-        "sha256": "c875709ccafe3493342776b28c8aa7b34e1fb800e2fccedcb499e6490e6ad1c0"
+        "sha256": "747d3a279349208ce8f5c6121bbf8ea039ebafaa8251c520ba3092a7aa80013f"
       },
       {
         "path": "src/core-compat.ts",
-        "sha256": "3638272a91166a047c3edc14626c0011e91b2de862a197d1b8e424470e7a0575"
+        "sha256": "53747612facd41ade5c291949b854d354e694b733e1f294cb3e521193760ae26"
       },
       {
         "path": "src/index.ts",
-        "sha256": "395b27b317e575b94a1049cdb284db185e0ec382fbae1e588c78ff2398b2563f"
+        "sha256": "76c2dc1598e72d11df59319cc64fb2aa39b8c3af4eb3077f66598f4f2a3323c0"
       },
       {
         "path": "test/agents-sync.test.ts",
@@ -113,11 +113,11 @@
       },
       {
         "path": "test/cli.test.ts",
-        "sha256": "83d8c6a9d7e8d46b57bb2e5da47c0345e8a512bdcc2e7cc8c59e163ade41de10"
+        "sha256": "d9adcce84b509e00213bda59a0948eca90d83bdd2fdbbc86aee5ce11d9176940"
       },
       {
         "path": "test/command-count.test.ts",
-        "sha256": "9958e10a8adb80ee64baad0d91fb4c9a3b6e8801c6379f7ba5f8f5ab6c1f1716"
+        "sha256": "f744cfe02805f567312a196805ebc49486c3e2a8e3f64de1700be276481f0cc1"
       },
       {
         "path": "test/core-compat-guard.test.ts",
@@ -129,11 +129,11 @@
       },
       {
         "path": "test/core-import-floor.test.ts",
-        "sha256": "84e16e0f31608570f72575038ae246d9ff002671ade0e9f9fa6009dd862dfc03"
+        "sha256": "948ce5017d7b512f7f32c817f8d1f5cbc5ede7d7c3f2788456ec5d24b8983f14"
       },
       {
         "path": "test/discrimination-check-cli.test.ts",
-        "sha256": "cd7507c8ec1f621fea6f05596541235d09efbd215540b56b012cf465e06b6ba0"
+        "sha256": "d0ec5796bc526d45cdad9041ea7357afc065917b347cf5421ec7d2696106b08c"
       },
       {
         "path": "test/epoch-replay-cli.test.ts",
@@ -255,6 +255,22 @@
         "path": "test/mutation-registry.json",
         "sha256": "3e6f9bb105154121988da41568ff85573099235857ba25e76c4264c166b414ae"
       },
+      {
+        "path": "test/parallel-worktree-smoke.test.ts",
+        "sha256": "0522b12ccdf3db79215c4c42162ef970f4cba0c0af96208426ca0323c367d0ee"
+      },
+      {
+        "path": "test/plan-completeness-gate.test.ts",
+        "sha256": "be010af797aeae754a3dd3e9f6f25d6f01066d4bf2037a01322554453d943ee3"
+      },
+      {
+        "path": "test/qe-bridge-cli.test.ts",
+        "sha256": "336ba7657c55f5b958a0ebed5617f3bc3b1956017b9389bbe7c38137889f8f1b"
+      },
+      {
+        "path": "test/qe-bridge-manifest-drift.test.ts",
+        "sha256": "b7b4d9e0c1dcee32e972aab97273b04bdde9634433e7c22345793a677dfff300"
+      },
       {
         "path": "test/skills-verify-static-advisories.test.ts",
         "sha256": "b1140c20ec04d1c8ae67f97a42dbcece1e8e63c98a5de2c087f0359d27c25f17"
@@ -283,6 +299,18 @@
         "path": "test/workflow-legacy-shim.test.ts",
         "sha256": "47d35ec36aa4793ee5d61debf1d345e7d236ad21db27f052aa3e7add03852205"
       },
+      {
+        "path": "test/workflow-run-cli.test.ts",
+        "sha256": "ac0468d8e97795602e8b8298f278356a273309674483854cd136b99ddf6e39d4"
+      },
+      {
+        "path": "test/workflow-run-r2.test.ts",
+        "sha256": "d7f308ac9538b7e9d7dc8dcd0ce7cf8127f26b5aea1f44e9d44ac1500ad733fb"
+      },
+      {
+        "path": "test/workflow-run-read-plane.test.ts",
+        "sha256": "c56111e578500d690190f9fdb4ec44182a892c7a6c2c289896509c1229d7b06d"
+      },
       {
         "path": "test/workflow-trace-cli-surface.test.ts",
         "sha256": "28df4b51fff1dc80bb38671d56f548d859949d7a9e2f00e7045e732efc7c2e3d"
@@ -297,5 +325,5 @@
       }
     ]
   },
-  "signature": "jyIwJnH5LH3+Wrq8W19HGqMpqt8e0srMnfZH/atV2H3ddnlrYzMe0f7bvyigDpdLzVApxiq+Xna5z4psVILMDg=="
+  "signature": "/iL9GLKryxZjC2MS2xcwig3BkbaMG+FLHOW5yhYVOI6Oe8MOEFCqE0d+a/xIWgGfKBy6UMH3Alzf25qYmPldAA=="
 }

package/README.md

@@ -414,7 +414,7 @@ dz bundle --select news-digest,goap-research-ed25519 --out ./dist
 dz init --target claude-code --select design-thinking
 
 # Curated set by topic (recommended):
-dz setup --target claude-code --preset meta          # 18 development skills + self-learning
+dz setup --target claude-code --preset meta          # 20 development skills + self-learning
 
 # Full toolkit with orchestrated pipeline:
 npx @dzhechkov/keysarium init                        # 7-phase research + commands + memory
@@ -739,6 +739,82 @@ ever enter a work order.
 **When to use:** after `dz compounding` reports the replay as READY; before claiming that recall
 "works"; and any time you want the claim re-checked as the corpus grows.
 
+### Обратный мост QE: Claude-ревьюер из Codex-сессии — `dz qe-bridge`
+
+The cross-family rule ("the family that writes the code must not review it") was enforceable in one
+direction only. When **Codex hosts** the run there is no Claude agent plane to dispatch from — and
+`dz reqe`'s brief admits it: for a claude review family it prints `null` where the codex branch
+prints a ready command. `dz qe-bridge` is that missing vehicle: a plain-shell command that probes a
+Claude model, sends a Step-8-shaped brief over SCOPED extracts, and PARSES the verdict.
+
+```bash
+# MEASURED 2026-08-19 on this repo — reproducer: the exact command below, reviewing a real shipped feature
+$ dz qe-bridge --family claude --slug wave1-scorer-negation --coder-family codex --model opus
+dz qe-bridge: GRADE C from claude/opus — 7 finding(s) in 343s
+  report:  features/wave1-scorer-negation/08b_reqe_report.md
+  signoff: features/wave1-scorer-negation/.fa-state/qe-bridge/signoff-2026-08-19T18-48-45-545Z.json
+  settle:  dz reqe --slug wave1-scorer-negation --done --report features/wave1-scorer-negation/08b_reqe_report.md
+  the bridge REPORTS (any grade exits 0); gating stays with dz reqe and the host pipeline.
+
+# the same command with a binary that cannot answer — a failed call, and NO report to settle with
+$ DZ_QE_BRIDGE_CLAUDE_BIN=/bin/false dz qe-bridge --family claude --slug wave1-scorer-negation --coder-family codex
+dz qe-bridge: FAILED — probe-failed
+  no candidate model answered the liveness probe — opus: exit 1, no `OK` in 0 chars of stdout; sonnet: exit 1, …; haiku: exit 1, …
+  record: features/wave1-scorer-negation/.fa-state/qe-bridge/failed-2026-08-19T18-48-52-931Z.json
+  no report was written — an unparseable or absent review is never a passing one.
+
+# with a debt on record, the report settles it through the untouched fail-closed path
+$ dz reqe --slug add-x --done --report features/add-x/08b_reqe_report.md
+dz reqe: debt settled: re-QE grade C (report …) — settlement appended to features/add-x/08_qe_report.md
+```
+
+**When to use:** you are hosting a run outside Claude Code (Codex, CI, a plain terminal), you have
+just written code, and the independent reviewer must be the OTHER family. Also: whenever `dz reqe`
+lists a debt whose coder family is `openai`.
+
+**The reviewer runs isolated.** Both calls (probe and review) run from an EMPTY temporary directory
+with `--safe-mode --strict-mcp-config --tools '' --no-session-persistence`, and the verdict is read
+from the `--output-format json` **result envelope**. Why: customization output lands on the same
+stdout — MEASURED on this machine, a session-start plugin prints a banner ahead of the model's
+answer — so a crafted hook could otherwise print a complete grade-A signoff and a stream parser
+would believe it (reproducer: `features/qe-bridge-claude/07_code_changes/mutants/c1-forgery-repro.mjs`).
+Residue, stated: `--safe-mode` leaves ADMIN-MANAGED policy settings in force, and no flag proves
+which binary answered.
+
+**What makes the grade valid.** Three channels must EXIST and AGREE, each read **LAST-anchored**,
+and the marker must be the FINAL content of the answer:
+the terminal `QE-BRIDGE-SIGNOFF grade=<A-F> findings=<n>` line, the last fenced `qe-bridge-signoff`
+JSON block, and the report's own line-anchored `GRADE:` line. Repo content flows into the prompt and
+comes back quoted, so a planted earlier verdict must lose — and it does (there is a test whose
+fixture plants `grade=A` early and requires the genuine trailing `grade=D` to win). Extracts are
+DEFANGED on the way in, so quoted content can never mint a verdict. Empty, gradeless, marker-only or
+self-contradicting output is a **named failure** — one of 17 closed reasons (`envelope-unparseable`,
+`marker-not-terminal`, `findings-count-mismatch`, `grade-mismatch`, `ambiguous-grade`,
+`audit-write-failed`, `report-write-failed`, … ; closed BOTH ways — every one is produced by a real
+run in the suite and leaves a record) — with an audit record under
+`features/<slug>/.fa-state/qe-bridge/` and the raw stdout beside it, never `findings: []`. Finding
+numbers are the reviewer's: a missing, non-positive or duplicated `n` fails the call instead of being
+renumbered, and a marker whose `findings=<n>` disagrees with the block is `findings-count-mismatch`.
+
+**The record is auditable, not just a conclusion.** Every run writes a `runId`, the resolved
+executable plus `binOverride` (true whenever `DZ_QE_BRIDGE_CLAUDE_BIN` was used — the documented TEST
+SEAM; there is no `--claude-bin` flag), the prompt sha256, the byte offsets at which each channel was
+found, the `requestedOut` path and `reportWritten: true|false` — so "no report was written" is a
+stated fact rather than an inference from an absent file. Records and reports are written `0600` in a
+`0700` directory, through `O_EXCL`, with realpath containment that refuses a symlinked parent — and
+the state directory itself is contained the same way, before anything is created in it. The audit
+trail is written BEFORE the report and corrected after it, so `reportWritten` can only ever
+understate; if the trail cannot be written at all, the run FAILS (`audit-write-failed`) rather than
+shipping a verdict nobody can re-derive.
+
+**Exit codes:** `0` a signoff was parsed (ANY grade — a grade F still exits 0: the bridge reports, it
+does not gate), `1` a named failure, `2` a usage error. **Honest limits:** it proves the call was
+procedurally sound (a live model was probed, a scoped brief was sent, a self-consistent verdict came
+back); it cannot prove which model authored the text, and it cannot classify your secrets — the
+extracts you scope are what leaves the machine. RU: мост в обратную сторону — из Codex-сессии
+позвать независимого Claude-ревьюера и получить РАЗОБРАННЫЙ вердикт; пустой или безоценочный ответ —
+это названная ошибка, а не «чисто».
+
 ### Пересмотр после аварийного само-ревью — `dz reqe`
 
 The feature-adr pipeline's cross-model guard says *the model that writes code must not review it*.
@@ -1161,7 +1237,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
 | [@dzhechkov/skills-qe](https://www.npmjs.com/package/@dzhechkov/skills-qe) | 20 | Quality engineering — test-gen, coverage, chaos, defect intelligence, QCSD swarms |
 | [@dzhechkov/skills-reasoning](https://www.npmjs.com/package/@dzhechkov/skills-reasoning) | 4 | Generic reasoning & code-quality — investigate (root-cause), solid (SOLID/TDD), karpathy-guidelines, agents-md-creator |
 | [@dzhechkov/skills-ecc](https://www.npmjs.com/package/@dzhechkov/skills-ecc) | 20 | Claude-Code engineering craft — agent architecture, autonomous loops, framework patterns |
-| [@dzhechkov/skills-meta](https://www.npmjs.com/package/@dzhechkov/skills-meta) | 19 | Dev-process meta skills — explore, feature-adr, design-thinking, audit, skill-advisor, loop-plan-author |
+| [@dzhechkov/skills-meta](https://www.npmjs.com/package/@dzhechkov/skills-meta) | 20 | Dev-process meta skills — explore, feature-adr, design-thinking, audit, skill-advisor, loop-plan-author, decision-mockups (vendored mirror of `@dzhechkov/skills-decision-mockups`) |
 | [@dzhechkov/skills-academic](https://www.npmjs.com/package/@dzhechkov/skills-academic) | 5 | Thesis-defense toolkit — dissertation review, questions, doc-check, defense eval |
 | [@dzhechkov/skills-news](https://www.npmjs.com/package/@dzhechkov/skills-news) | 3 | *dz-original* — news digests (`news-digest`) + delta watches (`news-monitor`) + bundled `goap-research-ed25519` verified-research backend (mandatory) |
 | [@dzhechkov/skills-idea2prd](https://www.npmjs.com/package/@dzhechkov/skills-idea2prd) | 1 | *dz-original* — `idea2prd-manual`: idea/problem → PRD+ADR+DDD+C4+Pseudocode+Tests+Completion (9 checkpoints); bundles the analyst trio as a sources.json-tracked vendor ([ADR-0001](https://github.com/djd1m/dz-harness-hub/blob/main/docs/adr/0001-skill-canonicalization-and-dependency-model.md)) |
@@ -1178,7 +1254,7 @@ Each pack is an npm package — click through for the **full per-skill documenta
 
 | Preset | Skills | Description |
 |--------|--------|-------------|
-| `meta` | 18 | Development process (explore, goap-research, problem-solver, design-thinking, feature-adr, knowledge-extractor, understand-anything-bridge, agentshield-scan, adversarial-verifier, skill-advisor, audit) |
+| `meta` | 20 | Development process (explore, goap-research, problem-solver, design-thinking, feature-adr, knowledge-extractor, understand-anything-bridge, agentshield-scan, adversarial-verifier, skill-advisor, audit, loop-plan-author, decision-mockups) |
 | `qe-engineer` | 20 | Quality engineering (test-gen, coverage, chaos, defect, ...) |
 | `bto` | 1 | Build-Benchmark-Test-Optimize pipeline |
 | `health` | 8 | Medical AI (diagnostics, drugs, labs, clinical decisions) |
@@ -1208,6 +1284,7 @@ Get the whole set with `dz init --target claude-code --preset meta`, or pick one
 | `reflection-loop` | Standalone critique → revise cycle (≤3 rounds) for code, text, architecture or research | `/reflection-loop` · "critique this" / "review and improve" |
 | `structured-reasoning` | Picks the reasoning strategy (Tree-of-Thought / CoT / compression) and checks the conclusion follows | "reason about…" / "explore options" / "compare approaches" |
 | `skill-crystallizer` | Auto-creates skills from execution traces, combines skills, and repairs broken ones | "create skill from this" / "combine skills" / "fix skill" |
+| `decision-mockups` | Owner-facing DECISION PAGE — plain-language write-up + browser-frame before/after mockups + clickable option forks + a copy-answers export you paste back into the chat (a one-option fork is deleted as fake, and a deterministic G0–G14 gate blocks the page if it is not) | "объясни понятным языком" / "что сделано, польза, риски, из чего выбираем" / "покажи владельцу развилки и собери решения" / "оформи артефактом" |
 
 ### Standalone Packages (install via npx, no dz CLI needed)
 
@@ -1228,7 +1305,7 @@ Get the whole set with `dz init --target claude-code --preset meta`, or pick one
 
 > **A skill and its npx toolkit are not duplicates — they're a graduation.** Several skills (e.g. `feature-adr`, `design-thinking`) exist BOTH as a skill inside a `dz` preset AND as a standalone `npx` package. The preset's SKILL.md is **fully functional on its own** (the whole methodology — modules + references — travels with it, and it auto-activates by description), and it's the only way to compile that capability to the **non-Claude platforms** (Codex/OpenCode/Hermes/OpenClaude) via `dz`. The npx package adds **project-level runtime governance** around the same skill: a slash command, governance rules, a context shard, and (for feature-adr) reward-learning + `/harvest`. So: pick the **skill/preset** for a working capability across platforms; pick the **npx toolkit** when you want it as a governed, command-driven fixture of one project.
 
-## Design custom Workflow loops (`workflow` · `workflow-lint` · `workflow-trace`)
+## Design custom Workflow loops (`workflow` · `workflow run` · `workflow-lint` · `workflow-trace`)
 
 Custom loops used to be born by copy-pasting a 1470-line workflow script; nothing deterministic
 checked the copy. The loop-designer meta-factory replaces that: a versioned typed plan
@@ -1266,15 +1343,36 @@ rules honestly report `inconclusive` there, never a silent green). `dz workflow
 self-checks the shared-subsystem blob registry (checkpoints, model-resolver, trace, …) that the
 generator injects verbatim — edit the canonical TS in harness-core, regenerate, never the copies.
 
-**Scope, stated plainly: `dz` AUTHORS, GATES and READS loops — it never RUNS one.** There is no
-`dz workflow run`, and step 5 above is not a `dz` command: execution belongs to the Claude Code
-host's `Workflow({scriptPath})` runtime, which owns the agent dispatch the generated script calls
-into. So every claim on this page is about the plan, the generated script, the lint verdict, and the
-run's own trace file — not about runtime behaviour `dz` could observe itself. `dz workflow-trace`
-reads what a HOST run already wrote (`trace.jsonl`, seq-ordered by the loop's own counter); with no
-host run there is nothing to read, and it says so rather than inventing a timeline. Portability
-follows from the same boundary: on a non-Claude-Code target the authoring and lint verbs work
-unchanged, and only execution is absent.
+**Scope, stated plainly (and NARROWED since `dz workflow run` shipped): `dz` AUTHORS, GATES, READS
+and now RUNS loops — but it never runs a RENDERED SCRIPT.** Step 5 above is still not a `dz`
+command: executing the generated script belongs to the Claude Code host's `Workflow({scriptPath})`
+runtime, which owns the agent dispatch that script calls into. What `dz workflow run` executes is
+the PLAN (see "Run a plan WITHOUT the Claude host" below) — a second, independent enactor that
+dispatches to `codex exec` / `claude -p` and writes the SAME trace shape. So a claim on this page is
+about the plan, the generated script, the lint verdict, and a run's own trace file — the two hosts
+are compared through the same reader, never assumed equivalent. `dz workflow-trace` reads what
+EITHER host wrote (`trace.jsonl`, seq-ordered by the loop's own counter); with no run there is
+nothing to read, and it says so rather than inventing a timeline.
+
+**Who writes the trace, and how far the cross-host claim actually reaches (MEASURED 2026-08-20).**
+The two enactors do not attest their runs the same way, and the difference is load-bearing:
+
+| Enactor | Who appends `trace.jsonl` | Evidentiary weight |
+|---|---|---|
+| `dz workflow run` (Codex **or** Claude family) | the `dz` process itself, `appendFileSync` in `cli.ts` | **instrument-written** |
+| the rendered script under the Claude host's `Workflow({scriptPath})` | an AGENT the script asks to run the flush command (`loop-render.ts`) | **agent-attested** |
+
+The host runtime's own records cannot substitute for the second row. `journal.jsonl` carries four
+fields (`type`, `key`, `agentId`, `result`) — no `seq`, no `ts`, so it can order nothing; the
+per-agent `agent-*.jsonl` transcripts do carry `timestamp` and `uuid`/`parentUuid`, so they can
+order AGENT runs — but a join, a gate redo and a typed pause are steps of the loop, not agents, and
+leave no record there at all.
+
+Consequently the cross-host structural equivalence proved by the committed fixture (`pkg-audit-1`)
+covers a bounded fanout, an all-activated join, a dep chain and a gate. It does **not** cover the
+gate redo route, the typed terminal route, the typed pause or the file deliverable: those four are
+what `discrimination.plan.json` adds, and no capture of them exists yet. Read every equivalence
+statement here as scoped to the first list.
 
 ### Build a loop for YOUR scenario — the end-to-end use case (a real one)
 
@@ -1441,6 +1539,97 @@ edit loop converges. What it cannot do is run the result: the generated script c
 `agent()`/`parallel()` sandbox, which only the Claude Code Workflow runtime provides. A green lint
 from Codex + a run under Claude Code is a legitimate two-agent split.
 
+### Run a plan WITHOUT the Claude host (`dz workflow run`)
+
+Everything above renders a plan into a script that only Claude Code's `Workflow({scriptPath})`
+runtime can execute. `dz workflow run` is the other half: it **interprets the plan itself**, from a
+plain shell, dispatching each step to `codex exec` or an isolated `claude -p`.
+
+**When to use which** — one sentence each:
+
+| | use it when |
+|---|---|
+| `workflow render` + `Workflow({scriptPath})` | you are already inside Claude Code and want the loop to run in that session, with its agents and its context |
+| `dz workflow run` | you are in a shell, in CI, or on a box with no Claude Code session — and you want the same plan enacted with a trace the same reader can read |
+
+It interprets the PLAN, never the rendered script (a rendered script is a Claude-host artifact; a
+second enactor reading it would be reading someone else's implementation). Same `loop-plan/1`, same
+gate grammar, same join policies, same failure classes — those decisions live in ONE module both
+enactors consume, not in two lookalike copies.
+
+```bash
+dz workflow run audit.plan.json --run-id pkg-audit-2 --coder-family claude
+# → dz workflow run: completed (pkg-audit-2) — trace at .dz/loop-trace/pkg-audit-2/trace.jsonl
+# → {"schema":"wf-run-result/1","runId":"pkg-audit-2","status":"completed","exitCode":0}
+
+# the run wrote into the addressing the reader already uses, so nothing new is needed to read it:
+dz workflow-trace --run pkg-audit-2 --invariants audit.plan.json
+# → INVARIANT PASS         seq-monotonic: seq unique and contiguous 1..12 (12 events)
+# → INVARIANT PASS         dispatch-settle-pairing: every dispatch has exactly one settle
+# → INVARIANT PASS         join-coverage:fan: every dispatched branch settled; …
+```
+
+**Exit codes — `run` and `workflow-lint` have DIFFERENT tables. Both, side by side:**
+
+| | 0 | 1 | 2 | 3 | 75 |
+|---|---|---|---|---|---|
+| `dz workflow run` | completed | failed (named reason) | usage / invalid plan | — | **typed pause** |
+| `dz workflow-lint` | clean | findings | — | inconclusive | — |
+
+`75` is `EX_TEMPFAIL` ("try again later"), and it is deliberately **not** `3`: `3` collides with
+lint's inconclusive and reads ignorable, while a pause strands work that is genuinely resumable.
+On a pause the **last stdout line** is a `wf-pause-envelope/1` JSON object; a FAILURE emits none —
+so a wrapper distinguishes the two from stdout and the exit code alone, without parsing prose.
+
+**Pause and resume** (a `kind: 'pause'` step, or the budget ceiling):
+
+```bash
+dz workflow run release.plan.json --run-id rel-7
+# → dz workflow run: PAUSED (AWAITING_APPROVAL) — resume with: dz workflow run release.plan.json --resume rel-7 --arg approve=<value>
+# → {"schema":"wf-pause-envelope/1","runId":"rel-7","exitCode":75,"pauseState":"AWAITING_APPROVAL", …}
+echo $?   # 75
+
+dz workflow run release.plan.json --resume rel-7 --arg approve=yes
+# → dz workflow run: completed (rel-7) — …
+```
+
+A resume never re-spends work: the cursor comes from checkpoint lines plus artifact probes, and a
+STALE-INPUT mismatch (plan digest, exec fingerprint, or the run-args hash) refuses to resume at all —
+there is no override, because the checkpoints describe a different run. Extending a ceiling is the
+one thing that is not an identity change: `--budget-extra` and `--wall-clock-extra` are recorded and
+capped, never silent.
+
+**Budget.** Every boundary reserves its worst case BEFORE it dispatches, so a region that will not
+fit pauses in front of the region rather than halfway through it. `budget.jsonl` gets one
+`wf-budget-1` row per dispatch (plus probe rows, which never decrement the ceiling).
+
+**Cross-model safety.** A step marked `x-role: "qe"` that resolves to the same family as
+`--coder-family` is REFUSED: the family that wrote the code may not review it. `--allow-same-family-qe`
+proceeds, and writes a real re-QE debt that `dz reqe` surfaces — a suspension you can see, not a
+comment nobody reads.
+
+#### Honest limits — three divergences from the Claude host, named rather than discovered
+
+1. **dz-side settle events carry no `wallTime`.** The Claude host stamps it shell-side during its
+   flush; the shared emitter accepts none, and stamping it afterwards would mean editing lines that
+   were already validated — exactly what the buffer discipline forbids. Per-dispatch wall clock
+   lives in `budget.jsonl` instead. `wallTime` was always diagnostic-only (never an operand of an
+   invariant), so no verdict changes.
+2. **The runner checkpoints every top-level stage unconditionally**, whatever `plan.checkpointing`
+   says. Its resume cursor is BUILT from those lines, so making them optional would make resume
+   optional. `plan.checkpointing` remains what it always was: the Claude-host opt-in.
+3. **A gate `terminal:` route ends the run by plan design, and leaves the trace INCOMPLETE.** This is
+   parity with the rendered script, whose top-level terminal `return` skips the epilogue that writes
+   `run.closed`. The run exits 0 (the plan declared this ending; the Workflow host completes too) and
+   the ledger row names the route — but `dz workflow-trace` will report the trace as incomplete and
+   downgrade window-truncated invariants to `inconclusive`. That is correct: nothing proves the
+   un-run steps would have passed.
+
+**Deferred, and said so:** budget rows do not appear in the `dz workflow-trace` timeline yet. The
+condition for adding them was zero reader change for Claude-host runs, and it is not met — a
+Claude-host run has no `budget.jsonl`, so the timeline would grow a section that is empty for half
+its inputs. `budget.jsonl` is readable by eye and by the recommender in the meantime.
+
 ### Move a run's telemetry to another machine (`workflow-trace export` / `import`)
 
 A run leaves traces on the machine that produced it. `export` puts one run's telemetry into a single
@@ -1511,9 +1700,9 @@ only at their documented scopes (plan + step), and `fanouts[].registry` items mu
 ItemKey domain the trace plane enforces — `trace.emit` can never decide whether a valid plan runs.
 Deferred options are on the loop-designer roadmap.
 
-## All Commands (68)
+## All Commands (69)
 
-*(67 MEASURED — reproducer: `grep -c "^      case '" src/cli.ts`, the dispatch cases.)*
+*(69 MEASURED — reproducer: `grep -c "^      case '" src/cli.ts`, the dispatch cases.)*
 
 ```
 dz setup             --target <name> [--preset <name>] [--select id,id,...] [--skills-dir <dir>] [--memory agentdb] [--no-memory] [--no-hooks] [--install-driver] [--force]
@@ -1579,6 +1768,7 @@ dz epoch-replay --judge <filled-work-order.json> [--out <file>] [--json]   # bli
 dz epoch-replay --score <judgments.json> --work-order <file> [--slice <name>] [--json]   # un-blind against the VERIFIED pre-registered assignment; ONE paired binomial over DECISIVE pairs (ties excluded, reported) → SUPPORTED only when the lift interval (2p−1) lies entirely above zero; FALSIFIED only on harm or a passed non-superiority test (lift upper bound below the margin PRE-REGISTERED in the work order, default 0.05, at 10+ decisive pairs); else INCONCLUSIVE (min 5 decisive pairs). Refuses a forged work order, a --margin flag, or duplicate judgement ids; the verdict is data, not an exit code
 dz score             --slug <feature> [--project <dir>] [--json]   # process scorecard for ONE feature-adr run, from its artifacts: ADR confirmation, discrimination proof, cross-model QE grade, live verification, README-first, learning loop, amendments — DESCRIPTIVE-ONLY (a low score exits 0); evidence lines are shown so the reader judges the heuristics
 dz reqe              [--slug <feature> [--done --report <f>]] [--project <dir>] [--json]   # the re-QE debt ledger: a usage-switched feature-adr run whose Step-8 QE ran on the coder's OWN family (cross-model guard suspended, FR-2.9) records a debt; list debts (also surfaced by dz usage), print the cross-family review brief, settle FAIL-CLOSED against an existing GRADED report (the run's own 08_qe_report.md — even hard-linked — can never settle its own debt); settlement lands in 08_qe_report.md, evidence rotates to reqe-settled.json
+dz qe-bridge         --family claude --slug <feature> [--coder-family codex|claude] [--model <id>] [--files a,b] [--out <f>] [--timeout <s>] [--allow-same-family] [--json]   # the REVERSE QE bridge (Codex-hosted → Claude reviewer): the reviewer runs ISOLATED (an empty temp cwd + --safe-mode --strict-mcp-config --tools '' --no-session-persistence, so no CLAUDE.md/skills/plugins/hooks/MCP load) and its verdict is read from the --output-format json RESULT ENVELOPE, so text a customization printed onto the same stdout can never become a signoff. Probes the model first; sends SCOPED extracts under a loud 200k-char ceiling; the grade must agree across three LAST-anchored channels AND the marker must be the final content — empty/gradeless/mismatched/miscounted output is a named failure with an audit record under features/<slug>/.fa-state/qe-bridge/, never a clean review. exit 0 signoff parsed (ANY grade — it reports, it does not gate) / 1 named failure / 2 usage. DZ_QE_BRIDGE_CLAUDE_BIN is a TEST SEAM (recorded as binOverride:true)
 dz backlog <sub>     add "<idea>" | list | show <id> | goals [--validate] | roulette [--seed n] [--commit <id>] | ship <id…> | drop <id…> | reopen <id…> | enrich <id> | jira <id> | harmonize [--apply]   # brain-backed idea backlog: capture an idea → semantic dedup against past ideas/features via the REUSED agentdb vector engine (two-signal: bounded-excerpt cosine DUPLICATE≥0.92 corroborated by shared subject vocabulary — a register-only 0.94 is demoted to RELATED, a length-only re-capture is caught as a subset duplicate; absorbed texts kept in absorbed.jsonl) + GoalMap alignment ("map+compass") → weighted seeded roulette picks one to work on → enrich STAGES an idea2prd hand-off → jira writes an auditable outbox via a configurable MCP adapter seam (jira-mcp|copilot-mcp|none). No 2nd vector store; without agentdb it degrades to exact-text dedup (honest)
 dz sign --init --out <path>  |  --pack <dir> --key <path>   # --init: generate the Ed25519 keypair (private OUTSIDE the repo, prints the public key for keys/dz.pub); else sign a pack's manifest + CycloneDX SBOM
 dz sbom --pack <dir> [--out <file>]   # emit the CycloneDX 1.5 SBOM for a pack standalone (file-level bill of materials); print to stdout or write to a file
@@ -1592,10 +1782,11 @@ dz auto-canonicalize --source <github-url> --pack <skills-pack>
 dz sync-upstream     [--package <dir>] [--list] [--all]
 dz drift-check       [--all] [--json] [--project <dir>]   # CI gate: exit 1 on NEW shared-skill drift (baseline: .dz/drift-allowlist.json; --all incl .claude dogfood)
 dz agents-sync       [--check] [--json] [--project <dir>] # sync anchored bearing rules into the root AGENTS.md policy fence; exit 0 sync / 1 drift / 3 inconclusive
-dz hooks-sync        --target codex [--check] [--remove] [--json]  # install + ARM the dz veto/recall hooks in $CODEX_HOME/hooks.json; exit 0 armed+trusted / 1 not armed / 3 inconclusive
+dz hooks-sync        --target codex [--check] [--verify|--no-verify] [--project <dir>] [--remove] [--json]  # install + ARM the dz veto/recall hooks in $CODEX_HOME/hooks.json and PROVE they fire with a live veto probe; exit 0 armed+trusted+verified / 1 not armed / 3 inconclusive (incl. --no-verify)
 dz sync-canonical    <skill> [--check] [--from <dir>] [--auto] [--project <dir>]   # heal every copy from skills-meta/<skill> or --from; no canonical + --check = compare copies to each other (exit 1 on drift); no canonical + write = refuse unless --auto (LOUD, picks most-complete copy); --check writes nothing
 dz scout             [--topics <list>] [--since <date>] [--deep] [--output <file>] [--diff] [--report]
 dz workflow          init --name <n> [--pattern pipeline|barrier|fanout|gate] [--o <plan.json>] | validate <plan.json> [--json] | render <plan.json> --o <script.js> [--check] [--force] | blobs [--check]   # loop-plan/1 authoring (the ADR-005 templates are retired)
+dz workflow run      <plan.json> [--run-id <id>] [--resume <runId>] [--arg k=v]... [--coder-family codex|claude] [--default-family codex|claude] [--budget <n>] [--max-wall-clock <s>] [--stage-timeout <s>] [--budget-extra <n>] [--wall-clock-extra <s>] [--run-dir <dir>] [--allow-same-family-qe] [--json]   # INTERPRET the plan without the Claude host; exit 0/1/2/75 (75 = typed pause)
 dz workflow-lint     <script.js> [--plan <plan.json>] [--require-plan|--legacy] [--json]   # 18-rule deterministic gate; exit 0/1/3 — inconclusive is never a pass
 dz workflow-trace    <runDir|--slug <s>|--run <id>> [--invariants <plan.json>] [--html <out.html>] [--json]   # timeline + SEQ invariant runner over the loop's own trace.jsonl
 dz workflow-trace export <run> --o <file> [--include-pairs --yes] [--strict]   # one run's telemetry as ONE movable file
@@ -2249,18 +2440,36 @@ install rewrites nothing and the hook keeps its trust.
 
 ```console
 $ dz hooks-sync --target codex
-dz hooks-sync: codex hooks installed and ARMED (trust: trusted) — ready
+dz hooks-sync: codex hooks installed and ARMED (trust: trusted) — VERIFIED by a live veto probe — ready
 
-$ dz hooks-sync --target codex --check
-dz hooks-sync: codex hooks installed and ARMED (trust: trusted) — ready
+$ dz hooks-sync --target codex --check          # read-only, and it re-proves the guard fires
+dz hooks-sync: codex hooks installed and ARMED (trust: trusted) — VERIFIED by a live veto probe — ready
+
+$ dz hooks-sync --target codex --no-verify      # skips the probe — and can never say "ready"
+dz hooks-sync: installed+trusted, NOT verified — ARMED = NO (trust: trusted, executable: true, verify: not verified (no live probe ran))
 
 $ dz hooks-sync --target codex --remove
 dz hooks-sync: removed 2 managed entr(ies) from /root/.codex/hooks.json
 ```
 
-Exit codes are **0** for armed **and** trusted, **1** for not-armed / drift / a refusal, and **3**
-when the answer is inconclusive (including "no `codex` binary on PATH", where dz writes **nothing**).
-`--check` writes nothing and is **silent** in a home that never opted in.
+**"ready" means a command was actually blocked, in this run.** By default `dz hooks-sync` runs a
+LIVE, nonce-scoped veto probe through `codex exec` in a hermetic workspace: it asks Codex to run one
+forbidden command and requires BOTH halves of the evidence — dz's `DZ-VETO:` marker in the
+transcript AND the absence of the command's side effect. `--dangerously-bypass-hook-trust` is never
+passed, because a bypassed run proves the helper body works and nothing about the installed state.
+Anything else — a silent transcript, a dead invocation, a timeout, a version mismatch — is
+**inconclusive**, never ready. `--no-verify` skips the probe and is reported as unverified;
+`--project <dir>` runs the probe in a project that has already opted into `"shellVeto": "block"`
+instead of the hermetic workspace.
+
+Exit codes are **0** for armed **and** trusted **and** verified, **1** for not-armed / drift / a
+refusal, and **3** when the answer is inconclusive (including "no `codex` binary on PATH", where dz
+writes **nothing**, and `--no-verify`, where nothing was measured). `--check` writes nothing and is
+**silent** in a home that never opted in.
+
+**`dz setup --target codex` and `dz init --target codex` deliver these hooks too**, verify them the
+same way, and report a failure without aborting the rest of the command. Pass `--no-hooks` for
+skills only.
 
 **What the two hooks do.**
 
@@ -2574,7 +2783,7 @@ dz pretrain                                     # detects stack, recommends pres
 dz recommend "work on this Node.js API"         # suggests skills + toolkits
 
 # 2. Install skills (choose your level)
-dz setup --target claude-code --preset meta --memory agentdb  # 18 skills (includes feature-adr)
+dz setup --target claude-code --preset meta --memory agentdb  # 20 skills (includes feature-adr)
 dz setup --target claude-code --preset qe-engineer             # + 20 QE skills
 
 # Want the full feature-adr toolkit with /feature-adr command + governance?
@@ -3748,9 +3957,18 @@ npx @dzhechkov/p-replicator init
 
 ## Status
 
-`v0.4.8` — staged (not yet published). Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
+`v0.5.1` — **published 2026-08-20**. Ships `dz workflow run`, the portable plan enactor: it INTERPRETS a `loop-plan/1` plan instead of executing a rendered script, dispatching to `codex exec` or an isolated `claude -p`, exit 0/1/2/75 (75 = a typed pause whose last stdout line is a `wf-pause-envelope/1`). Requires `@dzhechkov/harness-core >= 0.5.1` (the compat guard refuses below it by name). See "Who writes the trace" above for the stated scope of the cross-host equivalence claim — it is narrower than "the two hosts agree".
+
+`v0.5.0` — published. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
+
+New in 0.5.0 (feature `qe-bridge-claude`, cross-runtime leg 3/4): `dz qe-bridge --family claude`
+runs an INDEPENDENT Claude reviewer from any host — a Codex session included — and lands a PARSED
+signoff whose grade must agree across three LAST-anchored channels; an empty or gradeless answer is
+a named failure with a forensic record, never a clean review. `withNamedLockSync` generalises the
+store lock and now guards the `$CODEX_HOME/hooks.json` read-merge-write, so two dz processes can no
+longer lose each other's hook entries.
 
-New in 0.4.8 (feature `crossrt-1-agents-md`): `dz agents-sync` ports the fixed registry of bearing
+Also in 0.4.8 (feature `crossrt-1-agents-md`): `dz agents-sync` ports the fixed registry of bearing
 rules into an early root-`AGENTS.md` fence, `--check` exposes source drift to CI, and both surfaces
 report the measured Codex project-doc byte budget. A live cold-start probe, not file presence,
 remains the runtime acceptance gate.