@webpresso/opencode-plugin 3.1.11 → 3.1.13

package/README.md

@@ -3,9 +3,12 @@
 `@webpresso/opencode-plugin` is the OpenCode host adapter package for Agent
 Kit. It provides the native OpenCode npm plugin surface, registered through
 `opencode.json`, with the package module exports and metadata OpenCode expects.
+It also ships the same catalog-owned default `skills/` payload as the Claude
+and Codex adapter packages for host/package parity.
 
 The root `@webpresso/agent-kit` package is CLI/core only: it ships `wp`, MCP
 tools, audits, blueprints, session memory, docs, and catalog sources, but it
 does not ship this OpenCode payload from the root package. OpenCode delivery is
 native npm plugin registration only; there is no generated bridge, MCP bridge,
-or MCP injection payload in this package.
+or MCP injection payload in this package, and no `.opencode/skills` fallback is
+projected.

package/index.js

@@ -18,7 +18,13 @@ function extractDenyReason(envelope) {
   return null;
 }
 
+function extractUpdatedInput(envelope) {
+  const output = envelope?.hookSpecificOutput;
+  return output?.permissionDecision === "allow" ? (output.updatedInput ?? null) : null;
+}
+
 function hookInputForTool(tool, args, directory) {
+  const toolArgs = args && typeof args === "object" && !Array.isArray(args) ? args : {};
   const base = {
     cwd: directory,
     hook_event_name: "PreToolUse",
@@ -30,7 +36,8 @@ function hookInputForTool(tool, args, directory) {
         ...base,
         tool_name: "Bash",
         tool_input: {
-          command: args?.command ?? "",
+          ...toolArgs,
+          command: toolArgs.command ?? "",
         },
       };
     case "write":
@@ -181,6 +188,11 @@ export const WebpressoHooksPlugin = async ({ $, directory }) => {
         if (denyReason !== null) {
           throw new Error(denyReason);
         }
+        const updatedInput = extractUpdatedInput(envelope);
+        const nextCommand = updatedInput?.command;
+        if (input?.tool === "bash" && typeof nextCommand === "string") {
+          output.args.command = nextCommand;
+        }
       }
     },
     "tool.execute.after": async (input, output) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@webpresso/opencode-plugin",
-  "version": "3.1.11",
+  "version": "3.1.13",
   "private": false,
   "description": "OpenCode plugin adapter package for Webpresso agent-kit.",
   "homepage": "https://github.com/webpresso/agent-kit#readme",
@@ -15,6 +15,8 @@
   },
   "files": [
     "index.js",
+    "plugin-skill-ownership.json",
+    "skills",
     "LICENSE",
     "README.md"
   ],

package/plugin-skill-ownership.json

@@ -0,0 +1,84 @@
+{
+  "schemaVersion": 1,
+  "host": "opencode",
+  "packageName": "@webpresso/opencode-plugin",
+  "packageVersion": "3.1.13",
+  "runtimeDirs": [],
+  "skills": {
+    "autopilot": {
+      "digest": "sha256:7fc1fe9f5fb5b8a3e755f8e3ac4b807e4f140288544ffcf39e4cbfdea984014d"
+    },
+    "autoresearch": {
+      "digest": "sha256:b4d51cd53beb4a3271827172dfbd0b1d27bd58761ca07a35d49a5d6324b87fdf"
+    },
+    "best-practice-research": {
+      "digest": "sha256:b0d355c7f4afe9c38be83e293788bf582bea068c1db2fa5c45400441e315735d"
+    },
+    "browse": {
+      "digest": "sha256:21fd24862e7f7c8a1feadea6bc376492b136b99fc381cf1b8927c9db80615431"
+    },
+    "claude": {
+      "digest": "sha256:b75a472594d78bd9452c07fd791a426864848a2c9c726454dc72daf3813ae22b"
+    },
+    "codex": {
+      "digest": "sha256:803cea9c1b37406d7bdc8e44e9d5e9f3988218277500d8d6cb0d955c933c3302"
+    },
+    "deep-research": {
+      "digest": "sha256:01dafd194066a2936db0b437fd5c3beef6d7ff82478d0d995393093d89496f18"
+    },
+    "design-review": {
+      "digest": "sha256:5b213735e2842568774572f36b198bccf03c03a54b2732484aadd023f04acb23"
+    },
+    "devex-review": {
+      "digest": "sha256:306355888da0827e3523022077f731845726bbaaf595ca12515cc91d8605b5e6"
+    },
+    "fix": {
+      "digest": "sha256:e43dfad198f7279ebc2dca9e62f43fd960c783ca0ab25f133668fca13aed96b2"
+    },
+    "goal": {
+      "digest": "sha256:85380b633cfaaff8ec1639dd3a88412a41920aae3e8531de95e2b79411926a18"
+    },
+    "hooks-doctor": {
+      "digest": "sha256:3bfb0af64ff6796c56d51e4cd2bede7fb24c869f89b292546ea13ad2f5d3bb73"
+    },
+    "lore-protocol": {
+      "digest": "sha256:a80fbacc765e8b886437b9fdf7dd71e1ceb1b98b939078ec90fc88d06a8b4c69"
+    },
+    "opencode-go": {
+      "digest": "sha256:ccb2bcf09cc1c5c0d54027b84f580e688f5f5cf624e6cdc19870bd3ce99940fc"
+    },
+    "plan-ceo-review": {
+      "digest": "sha256:4d426158518dd71f8998770e8d4037bcbfa3c65d7265a93a4a78a9b015ba881e"
+    },
+    "plan-design-review": {
+      "digest": "sha256:a8a33efe67844d0602ff595c0b7e8f5529e52f51a781112952636c91963ce19e"
+    },
+    "plan-devex-review": {
+      "digest": "sha256:a49b4f61f1c54a7d89111c270616684dcbf2a7236bc817fafb5919366a7cda31"
+    },
+    "plan-eng-review": {
+      "digest": "sha256:b728dad90254d4c9f81b3818321d34ab53519b79ce20ff3bfe08bfacb2aa3e86"
+    },
+    "plan-refine": {
+      "digest": "sha256:891e84ff8592b8489b59e8642f6a602c9558fd57edd171af98499c94e2f62f13"
+    },
+    "ralplan": {
+      "digest": "sha256:db285d477f43ed23df990d4c03750d9916cdc7809356c1bf025efdf6a9add9ed"
+    },
+    "team": {
+      "digest": "sha256:151ef81df917435073a2d7b41173d33c45cb8aa1e5fdf34a70043bb3a2e746ff"
+    },
+    "tech-debt": {
+      "digest": "sha256:8b1f30e55ec6e5ab185ff19ecf15384438dbd619f675c2c65f2e53cedecbae5c"
+    },
+    "testing-philosophy": {
+      "digest": "sha256:43fa05bcb7eaf8efd4a8dcc0f9fb9c30ae9f80079d9b3dbfdc926734a64a2973"
+    },
+    "tph": {
+      "digest": "sha256:bed3684a850651534f315d355cdeae50d951c429817df0f105cccdb7f4e1561b"
+    },
+    "verify": {
+      "digest": "sha256:ce0dd3a77508d1bf11c805dec2de04e75b689201d376b2ff0fa957604d584500"
+    }
+  }
+}

package/skills/autopilot/SKILL.md

@@ -0,0 +1,39 @@
+---
+type: skill
+slug: autopilot
+title: Autopilot
+status: active
+scope: repo
+applies_to: [agents]
+related: [goal, plan-refine, verify, testing-philosophy]
+created: "2026-07-10"
+last_reviewed: "2026-07-10"
+name: autopilot
+description: "Drive a brief through the bounded native goal pipeline."
+argument-hint: "<brief|force: brief>"
+---
+
+# Autopilot
+
+Drive an approved brief through `plan -> execute -> qa -> validate -> land -> complete` using `wp goal run` and the current handoff.
+
+## Vague gate
+
+A brief is anchored when it includes a file path, symbol, issue number, test name, or numbered steps. Route any unanchored brief through `plan-refine` before execution. A leading `force:` is the only explicit bypass; strip it before creating the goal and record the bypass in the blueprint.
+
+## Pipeline
+
+1. Plan: refine blueprints and satisfy provenance-backed promotion approvals.
+2. Execute: implement current ready tasks; use only `wp_blueprint_task_verify` to mark them done.
+3. QA: run affected checks and `wp qa`; preserve normalized failure evidence.
+4. Validate: obtain distinct verification and code-review evidence and resolve findings. Each lane appends a tracked `reviews.md` record in one of these exact forms:
+
+   ```text
+   <!-- wp:goal-validation {"kind":"verify","reviewer":"<identity>","artifact":"<tracked-path>"} -->
+   <!-- wp:goal-validation {"kind":"code-review","reviewer":"<different-identity>","artifact":"<tracked-path>"} -->
+   ```
+
+5. Land: require green PR checks, complete the blueprint in the same PR, merge, and run owner cleanup.
+6. Complete: stop only when `wp goal run` records terminal evidence.
+
+Resume from durable state after interruption. Obey `WP_GOAL_DISABLE=1`, iteration/error/validation caps, and repository ownership. The pipeline must never self-approve, directly mark tasks done, bypass evidence, or push to main. Keep every loop bounded and never increase timeouts.

package/skills/autoresearch/SKILL.md

@@ -0,0 +1,49 @@
+---
+type: skill
+slug: autoresearch
+title: Autoresearch
+status: active
+scope: repo
+applies_to: [agents]
+related: [deep-research, best-practice-research, plan-refine, verify]
+created: "2026-07-13"
+last_reviewed: "2026-07-13"
+name: autoresearch
+description: "Artifact-gated research loop with explicit validation."
+argument-hint: "<research mission and validator>"
+---
+
+# Autoresearch
+
+Use when the user wants research to continue until a concrete validator accepts the result. This is for bounded research deliverables, not quick factual lookup or ordinary planning context.
+
+## Boundary
+
+- Use `deep-research` for one-pass citation-backed reports.
+- Use `best-practice-research` for focused upstream guidance.
+- Use `autoresearch` when completion depends on an explicit evaluator, benchmark, review rubric, or acceptance artifact.
+
+## Workflow
+
+1. Define the research mission, output artifact path, validator, and stop condition.
+2. Choose one validation mode:
+   - command validator: a repo command or script must pass and write the result.
+   - review validator: an independent review must approve the produced artifact against the mission.
+3. Create or update the durable research artifact before iterating.
+4. Gather sources and repo context until the artifact addresses the mission and cites material claims.
+5. Run the validator. If it fails, preserve the failure evidence, revise the artifact, and repeat.
+6. Stop only when the validator passes or a blocker prevents more evidence-gathering.
+
+## Output
+
+Return:
+
+- mission
+- artifact path
+- validation mode
+- validator command or review rubric
+- evidence gathered
+- pass/fail result
+- remaining gaps or blocker
+
+Do not treat elapsed turns, model confidence, or a draft report as completion evidence. Completion requires the declared validator to pass.

package/skills/best-practice-research/SKILL.md

@@ -0,0 +1,89 @@
+---
+name: best-practice-research
+description: "Official/upstream best-practice research wrapper with bounded evidence and dated citations."
+argument-hint: "<technology|decision|practice question>"
+---
+
+# Best-Practice Research
+
+Use this skill when a task depends on current external best practices, version-aware guidance, standards, official recommendations, or upstream behavior. This is a workflow wrapper: it routes evidence gathering and synthesis; it is not a new research authority and it does not replace `researcher`.
+
+## Purpose
+
+Produce a cited, reusable best-practice answer or handoff that separates current external evidence from repo-local facts and dependency-selection decisions.
+
+## Activate When
+
+- The user asks for best practices, recommended approach, current guidance, official recommendations, standards, or version-aware external behavior.
+- `$ralplan`, `$deep-interview`, `$team`, or another workflow needs current external evidence before planning or execution can be correct.
+- The task involves an already chosen technology and needs authoritative usage guidance, migration notes, API behavior, lifecycle rules, or current safety guidance.
+
+## Do Not Activate When
+
+- The answer is fully repo-local; use `explore` for codebase facts.
+- The main question is whether to adopt, replace, upgrade, or compare dependencies; use `dependency-expert`.
+- The user only needs implementation against already-grounded requirements; use `executor`, `$ralph`, or `$team` as appropriate.
+- The task can be answered from stable local project conventions without current external lookup.
+
+## Specialist Routing
+
+1. Use `explore` first for brownfield facts: current code usage, local constraints, versions, config, and integration points.
+2. Use `researcher` for official/upstream docs, release notes, standards, migration guides, source-backed examples, and current best-practice evidence for an already chosen technology.
+3. Use `dependency-expert` only for adoption/upgrade/replacement/comparison decisions.
+4. Return to the caller with explicit evidence, uncertainty, and any implementation handoff constraints.
+
+## Source-Quality Rules
+
+- Prefer official documentation, upstream source, release notes, changelogs, standards, and maintainer guidance.
+- Include source URLs for material claims.
+- State date/version context for current best-practice claims.
+- Label third-party summaries as supplemental; do not use them before official/upstream sources.
+- Flag stale, conflicting, undocumented, or version-mismatched evidence.
+- Do not over-fetch: gather the smallest evidence set that can support the decision.
+
+## Workflow
+
+1. Classify the question: conceptual best practice, implementation guidance, migration/version guidance, standards/compliance guidance, or mixed local + external guidance.
+2. Gather repo-local facts with `explore` when local usage or constraints affect the answer.
+3. Gather external evidence with `researcher` when current or version-aware practice affects correctness.
+4. Synthesize a concise answer with source quality, version/date context, caveats, and an implementation or planning handoff.
+5. Stop when the answer is grounded enough for the caller; otherwise report the exact blocker or specialist handoff needed.
+
+## Output Contract
+
+```md
+## Best-Practice Research: <question>
+
+### Direct Recommendation
+
+<actionable guidance or decision support>
+
+### Evidence Used
+
+- Official/upstream: <source URL> — <what it establishes>
+- Supplemental, if any: <source URL> — <why it is secondary>
+
+### Version / Date Context
+
+<versions, dates, release channels, or unknowns>
+
+### Repo-Local Context
+
+<facts from explore, or "not needed">
+
+### Boundaries / Non-goals
+
+<what this research does not decide>
+
+### Handoff
+
+<planning/execution/test implications>
+```
+
+## Stop Rules
+
+- Stop after a source-backed recommendation is reusable by the caller.
+- Stop and route upward if the task becomes dependency comparison, broad architecture, or implementation.
+- Do not continue researching when remaining work would only polish wording rather than change the recommendation.
+
+Task: {{ARGUMENTS}}

package/skills/browse/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: browse
+description: "Browser/page inspection via Webpresso Playwright: inspect DOM, console, network basics, screenshots, and findings."
+license: MIT
+allowed-tools:
+  - Read
+  - Glob
+  - Grep
+  - Bash
+---
+
+# Browse
+
+Use `wp browser doctor` first if browser availability is unknown; if it reports a missing browser, run `wp browser ensure chromium`. Prefer repo-local preview or dev-server URLs; if none are discoverable, ask for a URL.
+
+## Read-only inspection
+
+The `allowed-tools` frontmatter is an audited disclosure for supported hosts;
+pretool-guard remains the enforced mutation backstop when a host does not prove
+skill-frontmatter enforcement.
+
+1. Identify the URL and whether headed or headless mode is needed.
+2. Use `wp browser open <url> --json` for a lightweight smoke snapshot, or a project Playwright test for deeper flows.
+3. Report URL, title, status evidence, console/page errors when available, and any screenshots/artifacts.
+4. Do not mutate app data unless the user explicitly asks for a mutating browser flow.

package/skills/claude/SKILL.md

@@ -0,0 +1,154 @@
+---
+name: claude
+description: "Claude CLI outside-voice wrapper for review, adversarial challenge, or consultation from non-Claude hosts."
+license: MIT
+---
+
+# Claude outside voice
+
+Use when a non-Claude host needs Claude to review a diff, challenge a plan, or answer a focused repo question. Keep it bounded/read-only unless asked otherwise, and report Claude output as advice, not verified fact.
+
+## Auth check
+
+Use local Claude CLI login directly; do not route through Anthropic API-key env vars.
+
+```bash
+AUTH_STATUS_FILE=$(mktemp -t wp-claude-auth.XXXXXX)
+trap 'rm -f "$AUTH_STATUS_FILE"' EXIT
+if ! claude auth status --json >"$AUTH_STATUS_FILE" 2>/dev/null; then
+  if ! claude auth status >"$AUTH_STATUS_FILE" 2>/dev/null; then
+    echo "CLAUDE_AUTH=missing: run claude auth login with the intended Claude Max account"
+    exit 1
+  fi
+fi
+if grep -E '"(authenticated|loggedIn|success)"[[:space:]]*:[[:space:]]*true' "$AUTH_STATUS_FILE" >/dev/null; then
+  echo "CLAUDE_AUTH=cli-login"
+else
+  echo "CLAUDE_AUTH=missing: claude auth status did not report a recognized Claude CLI login"
+  exit 1
+fi
+```
+
+## Portable prompt file
+
+Use a suffix-free `mktemp -t` pattern so macOS and Linux both work:
+
+```bash
+PROMPT_FILE=$(mktemp -t wp-claude-review.XXXXXX)
+trap 'rm -f "$PROMPT_FILE"' EXIT
+```
+
+## Dashboard helper relation
+
+When this skill is invoked from `wp dash`, create explicit lifecycle records around the outside-voice call. The shared `wp dash-helper-*` service owns the event JSON and report shape; do not duplicate it in a skill. Outside the dashboard the block is a no-op, preserving standalone calls.
+
+```bash
+DASH_HELPER_RUN_ID=""
+if [ "${WP_DASH:-}" = "1" ] && [ -n "${WP_DASH_RUN_ID:-}" ]; then
+  DASH_HELPER_RUN_ID=$(wp dash-helper-start --provider claude --role reviewer)
+fi
+```
+
+Claude's managed native subagent lifecycle does not provide a reliable parent-linked completion event. It remains explicitly unsupported rather than being inferred from transcript text or timing.
+
+## Modes
+
+### Review
+
+Use single-file / single-question first for any non-trivial diff. Do not send a whole PR unless it already fits within the bounded payload below.
+
+**Model policy:** default to `sonnet` via `CLAUDE_REVIEW_MODEL=${CLAUDE_REVIEW_MODEL:-sonnet}`. Override to `opus` only when the review is approval evidence or the user explicitly asks for Opus. Never use `fable` for Claude outside-voice review. Any review used as blueprint approval evidence MUST run with Claude Opus and record `"model": "opus"`.
+
+#### Bounded prompt payload
+
+Always include:
+
+- current branch and base branch
+- `git diff --stat`
+- changed file list
+- one targeted file diff or one narrow snippet/hunk only, capped to a fixed size
+
+Prefer ~12 KB or ~200 lines per call. Split large reviews instead of raising the cap.
+
+```bash
+BASE_BRANCH=${BASE_BRANCH:-origin/main}
+CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+TARGET_FILE=${TARGET_FILE:?set TARGET_FILE to one changed file}
+
+{
+  printf 'Outside review mode: focused diff review\n'
+  printf 'Base branch: %s\nCurrent branch: %s\n\n' "$BASE_BRANCH" "$CURRENT_BRANCH"
+  printf 'git diff --stat %s...HEAD\n' "$BASE_BRANCH"
+  git diff --stat "$BASE_BRANCH"...HEAD
+  printf '\nChanged files:\n'
+  git diff --name-only "$BASE_BRANCH"...HEAD
+  printf '\nTarget file: %s\n' "$TARGET_FILE"
+  printf 'Bounded target diff (max 12000 bytes):\n'
+  git diff --unified=3 "$BASE_BRANCH"...HEAD -- "$TARGET_FILE" | \
+    head -c 12000
+  printf '\n\nQuestion: Identify the highest-signal correctness, security, data-loss, or maintainability risk in %s. Quote only the smallest relevant excerpt. If context is insufficient, answer INSUFFICIENT_CONTEXT.\n' "$TARGET_FILE"
+} >"$PROMPT_FILE"
+```
+
+#### Progress-aware review runtime
+
+Run both the availability probe and the full review through the typed `wp review run` owner. Skills must not embed subprocess supervision. The runtime consumes Claude's streaming JSON events, advances its idle clock only on monotonic semantic progress, and has no total wall-clock cutoff.
+
+```bash
+CLAUDE_REVIEW_MODEL=${CLAUDE_REVIEW_MODEL:-sonnet}
+CLAUDE_REVIEW_EFFORT=${CLAUDE_REVIEW_EFFORT:-medium}
+CLAUDE_REVIEW_PROBE_IDLE_SECONDS=${CLAUDE_REVIEW_PROBE_IDLE_SECONDS:-180}
+CLAUDE_REVIEW_IDLE_SECONDS=${CLAUDE_REVIEW_IDLE_SECONDS:-180}
+CLAUDE_REVIEW_ARTIFACT_ROOT=${CLAUDE_REVIEW_ARTIFACT_ROOT:-"$(pwd)/.webpresso/reviews"}
+PROBE_FILE=$(mktemp -t wp-claude-probe.XXXXXX)
+trap 'rm -f "$PROMPT_FILE" "$PROBE_FILE"' EXIT
+printf 'Reply exactly CLAUDE_OK.\n' >"$PROBE_FILE"
+
+wp review run \
+  --provider claude \
+  --prompt-file "$PROBE_FILE" \
+  --model "$CLAUDE_REVIEW_MODEL" \
+  --effort "$CLAUDE_REVIEW_EFFORT" \
+  --stage probe \
+  --expected-marker CLAUDE_OK \
+  --artifact-root "$CLAUDE_REVIEW_ARTIFACT_ROOT" \
+  --idle-seconds "$CLAUDE_REVIEW_PROBE_IDLE_SECONDS"
+
+wp review run \
+  --provider claude \
+  --prompt-file "$PROMPT_FILE" \
+  --model "$CLAUDE_REVIEW_MODEL" \
+  --effort "$CLAUDE_REVIEW_EFFORT" \
+  --stage review \
+  --artifact-root "$CLAUDE_REVIEW_ARTIFACT_ROOT" \
+  --idle-seconds "$CLAUDE_REVIEW_IDLE_SECONDS"
+CLAUDE_REVIEW_CODE=$?
+```
+
+After the review runtime exits, emit its terminal state using the same artifact path:
+
+```bash
+if [ -n "$DASH_HELPER_RUN_ID" ]; then
+  if [ "$CLAUDE_REVIEW_CODE" -eq 0 ]; then
+    wp dash-helper-complete --provider claude --run-id "$DASH_HELPER_RUN_ID" --role reviewer --outcome completed --artifact "${CLAUDE_REVIEW_ARTIFACT:-}"
+  else
+    wp dash-helper-complete --provider claude --run-id "$DASH_HELPER_RUN_ID" --role reviewer --outcome failed --artifact "${CLAUDE_REVIEW_ARTIFACT:-}"
+  fi
+fi
+```
+
+Treat `true-idle`, `protocol-unsupported`, provider failure, abort, spawn failure, or artifact failure as unavailable review evidence. Never replace them with a static timeout, arbitrary byte-growth heartbeat, or buffered-output fallback.
+
+#### Retry policy
+
+Do not perform blind retries. Run the full review once. Retry only after diagnosing and changing a command-shape problem; record the reason and artifact path. Do not fall back to an unbounded whole-PR prompt.
+
+Summarize findings with severity, evidence, model, artifact path, and whether you independently verified them.
+
+### Challenge
+
+Ask Claude to argue against the current plan: hidden assumptions, failure modes, missing tests, and simpler alternatives.
+
+### Consult
+
+Ask a focused repo question. Include only the necessary file paths and snippets; do not send secrets.

package/skills/codex/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: codex
+description: "Codex CLI outside-voice wrapper for code review, plan challenge, or consultation from non-Codex hosts."
+license: MIT
+---
+
+# Codex outside voice
+
+Use this skill from Claude or another non-Codex host when the user wants Codex to independently review a diff, challenge a plan, or answer a repo question. Keep Codex read-only by default and treat its answer as external advice until independently verified.
+
+## Auth check
+
+```bash
+if ! codex login status >/dev/null 2>&1; then
+  echo "CODEX_AUTH=missing: run codex login before using the codex outside-voice skill"
+  exit 1
+fi
+echo "CODEX_AUTH=ok"
+```
+
+## Portable prompt file
+
+```bash
+PROMPT_FILE=$(mktemp -t wp-codex-review.XXXXXX)
+trap 'rm -f "$PROMPT_FILE"' EXIT
+```
+
+## Dashboard helper relation
+
+When called by `wp dash`, register the outside-voice helper through the shared service rather than writing relationship JSON in this skill. This is intentionally a no-op for standalone use.
+
+```bash
+DASH_HELPER_RUN_ID=""
+if [ "${WP_DASH:-}" = "1" ] && [ -n "${WP_DASH_RUN_ID:-}" ]; then
+  DASH_HELPER_RUN_ID=$(wp dash-helper-start --provider codex --role reviewer)
+fi
+```
+
+After the review command completes, report the exact terminal outcome. Supply an artifact path when the caller created one.
+
+```bash
+if [ -n "$DASH_HELPER_RUN_ID" ]; then
+  if [ "${CODEX_REVIEW_CODE:-0}" -eq 0 ]; then
+    wp dash-helper-complete --provider codex --run-id "$DASH_HELPER_RUN_ID" --role reviewer --outcome completed --artifact "${CODEX_REVIEW_ARTIFACT:-}"
+  else
+    wp dash-helper-complete --provider codex --run-id "$DASH_HELPER_RUN_ID" --role reviewer --outcome failed --artifact "${CODEX_REVIEW_ARTIFACT:-}"
+  fi
+fi
+```
+
+Codex native subagent events are not currently parent-linked in the managed lifecycle. They are shown as unsupported, never inferred from text, PIDs, or timestamps.
+
+## Modes
+
+### Review
+
+1. Capture the current branch, base branch, and `git diff --stat`.
+2. Write a concise prompt asking Codex to find correctness, security, data-loss, and maintainability risks.
+3. Run Codex non-interactively in read-only mode:
+
+```bash
+CODEX_REVIEW_EFFORT=${CODEX_REVIEW_EFFORT:-medium}
+case "$CODEX_REVIEW_EFFORT" in
+  medium|high) ;;
+  *) echo "CODEX_REVIEW_EFFORT must be one of: medium, high" >&2; exit 2 ;;
+esac
+CODEX_REVIEW_CODE=0
+codex exec -c model_reasoning_effort="\"$CODEX_REVIEW_EFFORT\"" --sandbox read-only --cd "$PWD" - <"$PROMPT_FILE" || CODEX_REVIEW_CODE=$?
+```
+
+4. Summarize findings with severity, evidence, and whether you independently verified them.
+
+### Challenge
+
+Ask Codex to argue against the current plan: hidden assumptions, failure modes, missing tests, and simpler alternatives.
+
+### Consult
+
+Ask a focused repo question. Include only the necessary file paths and snippets; do not send secrets.