qa

name	qa
preamble-tier	1
version	0.1.0
description	Canonical Nexus QA command. Records governed validation scope, QA findings, and structured readiness state for the governed Nexus lifecycle. Use when the user says "QA the build", "validate the change", "run end-to-end checks before ship", or after `/review` passes and before `/ship` reads the verdict. (nexus)
allowed-tools	["Bash","Read","AskUserQuestion"]

Preamble (run first)

_UPD=$(~/.claude/skills/nexus/bin/nexus-update-check 2>/dev/null || .claude/skills/nexus/bin/nexus-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
mkdir -p ~/.nexus/sessions
touch ~/.nexus/sessions/"$PPID"
_SESSIONS=$(find ~/.nexus/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
find ~/.nexus/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
_CONTRIB=$(~/.claude/skills/nexus/bin/nexus-config get nexus_contributor 2>/dev/null || true)
_PROACTIVE=$(~/.claude/skills/nexus/bin/nexus-config get proactive 2>/dev/null || echo "true")
_PROACTIVE_PROMPTED=$([ -f ~/.nexus/.proactive-prompted ] && echo "yes" || echo "no")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$(~/.claude/skills/nexus/bin/nexus-config get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
_MODE_CONFIGURED=$(~/.claude/skills/nexus/bin/nexus-config get execution_mode 2>/dev/null || true)
_PRIMARY_PROVIDER_CONFIG=$(~/.claude/skills/nexus/bin/nexus-config get primary_provider 2>/dev/null || true)
_TOPOLOGY_CONFIG=$(~/.claude/skills/nexus/bin/nexus-config get provider_topology 2>/dev/null || true)
if command -v ask >/dev/null 2>&1; then
  _CCB_AVAILABLE="yes"
else
  _CCB_AVAILABLE="no"
fi
if [ -n "$_MODE_CONFIGURED" ]; then
  _EXECUTION_MODE="$_MODE_CONFIGURED"
  _EXECUTION_MODE_CONFIGURED="yes"
else
  _EXECUTION_MODE_CONFIGURED="no"
  if [ "$_CCB_AVAILABLE" = "yes" ]; then
    _EXECUTION_MODE="governed_ccb"
  else
    _EXECUTION_MODE="local_provider"
  fi
fi
if [ "$_EXECUTION_MODE" = "governed_ccb" ]; then
  _PRIMARY_PROVIDER="codex"
  _PROVIDER_TOPOLOGY="multi_session"
else
  if [ -n "$_PRIMARY_PROVIDER_CONFIG" ]; then
    _PRIMARY_PROVIDER="$_PRIMARY_PROVIDER_CONFIG"
  elif command -v claude >/dev/null 2>&1; then
    _PRIMARY_PROVIDER="claude"
  elif command -v codex >/dev/null 2>&1; then
    _PRIMARY_PROVIDER="codex"
  elif command -v gemini >/dev/null 2>&1; then
    _PRIMARY_PROVIDER="gemini"
  else
    _PRIMARY_PROVIDER="claude"
  fi
  if [ -n "$_TOPOLOGY_CONFIG" ]; then
    _PROVIDER_TOPOLOGY="$_TOPOLOGY_CONFIG"
  else
    _PROVIDER_TOPOLOGY="single_agent"
  fi
fi
_EFFECTIVE_EXECUTION=$(~/.claude/skills/nexus/bin/nexus-config effective-execution 2>/dev/null || true)
if [ -n "$_EFFECTIVE_EXECUTION" ]; then
  _EXECUTION_MODE=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^execution_mode:/{print $2; exit}')
  _EXECUTION_MODE_CONFIGURED=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^execution_mode_configured:/{print $2; exit}')
  _PRIMARY_PROVIDER=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^effective_primary_provider:/{print $2; exit}')
  _PROVIDER_TOPOLOGY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^effective_provider_topology:/{print $2; exit}')
  _EXECUTION_MODE_SOURCE=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^execution_mode_source:/{print $2; exit}')
  _EXECUTION_PATH=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^effective_requested_execution_path:/{print $2; exit}')
  _CURRENT_SESSION_READY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^current_session_ready:/{print $2; exit}')
  _REQUIRED_GOVERNED_PROVIDERS=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^required_governed_providers:/{print $2; exit}')
  _GOVERNED_READY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^governed_ready:/{print $2; exit}')
  _MOUNTED_PROVIDERS=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^mounted_providers:/{print $2; exit}')
  _MISSING_PROVIDERS=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^missing_providers:/{print $2; exit}')
  _LOCAL_PROVIDER_CANDIDATE=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_provider_candidate:/{print $2; exit}')
  _LOCAL_PROVIDER_TOPOLOGY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_provider_topology:/{print $2; exit}')
  _LOCAL_PROVIDER_EXECUTION_PATH=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_provider_requested_execution_path:/{print $2; exit}')
  _LOCAL_PROVIDER_READY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_provider_ready:/{print $2; exit}')
  _LOCAL_CLAUDE_AGENT_TEAM_READY=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_claude_agent_team_ready:/{print $2; exit}')
  _LOCAL_CLAUDE_AGENT_TEAM_REASON=$(printf '%s
' "$_EFFECTIVE_EXECUTION" | awk -F': ' '/^local_claude_agent_team_readiness_reason:/{print $2; exit}')
else
  _EXECUTION_MODE_SOURCE=""
  _EXECUTION_PATH=""
  _CURRENT_SESSION_READY="unknown"
  _REQUIRED_GOVERNED_PROVIDERS=""
  _GOVERNED_READY=""
  _MOUNTED_PROVIDERS=""
  _MISSING_PROVIDERS=""
  _LOCAL_PROVIDER_CANDIDATE=""
  _LOCAL_PROVIDER_TOPOLOGY=""
  _LOCAL_PROVIDER_EXECUTION_PATH=""
  _LOCAL_PROVIDER_READY=""
  _LOCAL_CLAUDE_AGENT_TEAM_READY=""
  _LOCAL_CLAUDE_AGENT_TEAM_REASON=""
fi
echo "CCB_AVAILABLE: $_CCB_AVAILABLE"
echo "EXECUTION_MODE: $_EXECUTION_MODE"
echo "EXECUTION_MODE_CONFIGURED: $_EXECUTION_MODE_CONFIGURED"
echo "EXECUTION_MODE_SOURCE: $_EXECUTION_MODE_SOURCE"
echo "PRIMARY_PROVIDER: $_PRIMARY_PROVIDER"
echo "PROVIDER_TOPOLOGY: $_PROVIDER_TOPOLOGY"
echo "EXECUTION_PATH: $_EXECUTION_PATH"
echo "CURRENT_SESSION_READY: $_CURRENT_SESSION_READY"
echo "REQUIRED_GOVERNED_PROVIDERS: $_REQUIRED_GOVERNED_PROVIDERS"
echo "GOVERNED_READY: $_GOVERNED_READY"
echo "MOUNTED_PROVIDERS: $_MOUNTED_PROVIDERS"
echo "MISSING_PROVIDERS: $_MISSING_PROVIDERS"
echo "LOCAL_PROVIDER_CANDIDATE: $_LOCAL_PROVIDER_CANDIDATE"
echo "LOCAL_PROVIDER_TOPOLOGY: $_LOCAL_PROVIDER_TOPOLOGY"
echo "LOCAL_PROVIDER_EXECUTION_PATH: $_LOCAL_PROVIDER_EXECUTION_PATH"
echo "LOCAL_PROVIDER_READY: $_LOCAL_PROVIDER_READY"
echo "LOCAL_CLAUDE_AGENT_TEAM_READY: $_LOCAL_CLAUDE_AGENT_TEAM_READY"
echo "LOCAL_CLAUDE_AGENT_TEAM_REASON: $_LOCAL_CLAUDE_AGENT_TEAM_REASON"
source <(~/.claude/skills/nexus/bin/nexus-repo-mode 2>/dev/null) || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
_LAKE_SEEN=$([ -f ~/.nexus/.completeness-intro-seen ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
# Learnings count
eval "$(~/.claude/skills/nexus/bin/nexus-slug 2>/dev/null)" 2>/dev/null || true
_LEARN_FILE="$HOME/.nexus/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
else
  echo "LEARNINGS: 0"
fi
# Check if CLAUDE.md already has Nexus routing guidance or an equivalent routing rule
_HAS_ROUTING="no"
if [ -f CLAUDE.md ]; then
  if grep -q "## Nexus Skill Routing" CLAUDE.md 2>/dev/null; then
    _HAS_ROUTING="yes"
  elif grep -Eiq 'route lifecycle work through .*?/discover.*?/closeout' CLAUDE.md 2>/dev/null; then
    _HAS_ROUTING="yes"
  elif grep -Fq "When the user's request matches a canonical Nexus command, invoke that command first." CLAUDE.md 2>/dev/null; then
    _HAS_ROUTING="yes"
  fi
fi
_ROUTING_DECLINED=$(~/.claude/skills/nexus/bin/nexus-config get routing_declined 2>/dev/null || echo "false")
echo "HAS_ROUTING: $_HAS_ROUTING"
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"

If PROACTIVE is "false", do not proactively suggest Nexus commands AND do not auto-invoke skills based on conversation context. Only run skills the user explicitly types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say: "I think /skillname might help here — want me to run it?" and wait for confirmation. The user opted out of proactive behavior.

If SKILL_PREFIX is "true", the user has namespaced Nexus commands. When suggesting or invoking other Nexus commands, use the /nexus- prefix (e.g., /nexus-qa instead of /qa, /nexus-ship instead of /ship). Disk paths are unaffected — always use ~/.claude/skills/nexus/[skill-name]/SKILL.md for reading skill files.

If output shows UPGRADE_AVAILABLE <old> <new>: read ~/.claude/skills/nexus/nexus-upgrade/SKILL.md and follow the release-based "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). /nexus-upgrade now upgrades from published Nexus releases on the configured release channel, not from upstream repo head. If JUST_UPGRADED <from> <to>: tell user "Running Nexus v{to} (just updated!)" and continue.

If JUST_UPGRADED <from> <to> is present, always include the standardized runtime summary before moving on to work, even when EXECUTION_MODE_CONFIGURED is yes.

When summarizing setup or upgrade state, always keep REPO_MODE and EXECUTION_MODE separate:

• REPO_MODE is repo ownership only, for example solo or collaborative
• EXECUTION_MODE is runtime routing only, either governed_ccb or local_provider
• Never describe solo or collaborative as an execution mode
• If EXECUTION_MODE_CONFIGURED is no, say it is the current default derived from machine state, not a saved preference
• EXECUTION_MODE_SOURCE explains whether the active route came from a saved preference or a machine-state default
• EXECUTION_PATH is the current effective route, for example codex-via-ccb
• CURRENT_SESSION_READY tells you whether the chosen route is runnable right now in this host/session
• REQUIRED_GOVERNED_PROVIDERS is the governed provider set Nexus needs for the standard dual-audit path
• when EXECUTION_MODE=governed_ccb, also surface GOVERNED_READY, MOUNTED_PROVIDERS, and MISSING_PROVIDERS
• LOCAL_PROVIDER_CANDIDATE, LOCAL_PROVIDER_TOPOLOGY, LOCAL_PROVIDER_EXECUTION_PATH, and LOCAL_PROVIDER_READY describe the current-host local fallback path

Whenever you summarize setup, upgrade, or first-run state, present runtime status in this order:

• Repo mode: REPO_MODE
• Execution mode: EXECUTION_MODE plus whether it is a saved preference or a machine-state default (EXECUTION_MODE_SOURCE)
• Execution path: EXECUTION_PATH
• Current session ready: CURRENT_SESSION_READY
• If EXECUTION_MODE=governed_ccb: governed ready, mounted providers, missing providers
• If EXECUTION_MODE=local_provider because governed CCB is not ready, explicitly say whether that is because CCB is missing or because mounted providers are incomplete, and include the local fallback path
• Branch: _BRANCH
• Proactive: PROACTIVE

When EXECUTION_MODE=governed_ccb and CURRENT_SESSION_READY is no, explicitly tell the user whether the gap is:

• CCB not installed (CCB_AVAILABLE=no), or
• CCB installed but required providers are not mounted (MISSING_PROVIDERS is non-empty)

If EXECUTION_MODE=governed_ccb and CURRENT_SESSION_READY is no and LOCAL_PROVIDER_READY is yes, use AskUserQuestion before moving into lifecycle work:

Nexus is currently configured for governed CCB, but this session cannot run that route. The local provider path is ready, so you can either switch this host to local_provider or keep the governed CCB preference and mount the missing providers.

RECOMMENDATION: Choose A if you want to work now in this host. Choose B only if you intend to mount CCB providers before continuing. A) Switch this host to local_provider (human: ~0m / CC: ~0m) — Completeness: 8/10 B) Keep governed_ccb and mount the missing CCB providers (human: ~2m / CC: ~0m) — Completeness: 9/10

If A:

~/.claude/skills/nexus/bin/nexus-config set execution_mode local_provider
if [ -n "$_LOCAL_PROVIDER_CANDIDATE" ]; then
  ~/.claude/skills/nexus/bin/nexus-config set primary_provider "$_LOCAL_PROVIDER_CANDIDATE"
fi
if [ -n "$_LOCAL_PROVIDER_TOPOLOGY" ]; then
  ~/.claude/skills/nexus/bin/nexus-config set provider_topology "$_LOCAL_PROVIDER_TOPOLOGY"
fi

Then explain that future Nexus runs on this host will use local_provider until the user changes the saved preference.

If B: do not change Nexus config. Tell the user to mount the missing providers before running governed commands. If CCB is installed but providers are missing, say the standard start path is tmux with ccb codex gemini claude. If CCB is not installed, say they need to install or restore CCB first.

If JUST_UPGRADED <from> <to> is present and EXECUTION_MODE_CONFIGURED is no, state the effective execution mode explicitly using EXECUTION_MODE, EXECUTION_MODE_SOURCE, and CCB_AVAILABLE. Use ~/.claude/skills/nexus/bin/nexus-config effective-execution when you need the effective provider, topology, or requested execution path. When EXECUTION_MODE=governed_ccb, do not ask the user to configure PRIMARY_PROVIDER or PROVIDER_TOPOLOGY. Those are local-provider host preferences, not governed CCB config keys.

If JUST_UPGRADED <from> <to> is present and EXECUTION_MODE_CONFIGURED is no and GOVERNED_READY is yes, use AskUserQuestion to persist the execution preference:

Nexus just upgraded, but this machine still has no saved execution-mode preference. Repo mode only tells you whether the repo is solo or collaborative. Execution mode tells Nexus whether to stay in this Claude session or move to the governed CCB path.

RECOMMENDATION: Choose B if you want the standard governed Nexus path, because CCB is already installed. Completeness: 9/10. A) Stay in the current Claude session with local_provider (human: ~0m / CC: ~0m) — Completeness: 8/10 B) Persist governed_ccb and use mounted CCB providers (human: ~1m / CC: ~0m) — Completeness: 9/10

If A:

~/.claude/skills/nexus/bin/nexus-config set execution_mode local_provider
~/.claude/skills/nexus/bin/nexus-config set primary_provider claude

Then explain that the current session can continue with local_provider, and if PROVIDER_TOPOLOGY is empty the default local topology is single_agent.

If B:

~/.claude/skills/nexus/bin/nexus-config set execution_mode governed_ccb

Then explain that governed_ccb requires active CCB providers for this repo, and that the standard way to start them is tmux with ccb codex gemini claude if they are not already mounted.

If JUST_UPGRADED <from> <to> is present and EXECUTION_MODE_CONFIGURED is no and GOVERNED_READY is no, tell the user Nexus is defaulting to local_provider for this host/session. If CCB_AVAILABLE is no, say that CCB is not detected. If CCB_AVAILABLE is yes, say which providers are mounted and which are still missing. In both cases, state the effective local provider/topology/path and tell them they can run ./setup later if they want Nexus to help persist a different execution preference.

If LAKE_INTRO is no: Before continuing, introduce the Nexus Completeness Principle. Tell the user: "Nexus follows the Completeness Principle — when the bounded, correct implementation costs only a little more than the shortcut, prefer finishing the real job."

Then run:

touch ~/.nexus/.completeness-intro-seen

This only happens once.

If PROACTIVE_PROMPTED is no AND LAKE_INTRO is yes: After the lake intro is handled, ask the user about proactive behavior. Use AskUserQuestion:

Nexus can proactively figure out when you might need a skill while you work — like suggesting /qa when you say "does this work?" or /investigate when you hit a bug. We recommend keeping this on — it speeds up every part of your workflow.

Options:

• A) Keep it on (recommended)
• B) Turn it off — I'll type /commands myself

If A: run ~/.claude/skills/nexus/bin/nexus-config set proactive true If B: run ~/.claude/skills/nexus/bin/nexus-config set proactive false

Always run:

touch ~/.nexus/.proactive-prompted

This only happens once. If PROACTIVE_PROMPTED is yes, skip this entirely.

If HAS_ROUTING is no AND ROUTING_DECLINED is false AND PROACTIVE_PROMPTED is yes: Check if a CLAUDE.md file exists in the project root. If it does not exist, create it. Before prompting, treat either the standard ## Nexus Skill Routing section or any existing instruction that routes lifecycle work through /discover to /closeout as equivalent Nexus routing guidance. If equivalent guidance already exists, skip this entirely.

Use AskUserQuestion:

Nexus works best when your project's CLAUDE.md includes canonical Nexus command routing guidance. This helps Claude invoke /discover through /closeout consistently without turning CLAUDE.md into a second contract layer.

Options:

• A) Add Nexus invocation guidance to CLAUDE.md (recommended)
• B) No thanks, I'll invoke Nexus commands manually

If A: Append this section to the end of CLAUDE.md only when the file does not already contain equivalent Nexus routing guidance:

## Nexus Skill Routing

When the user's request matches a canonical Nexus command, invoke that command first.
This guidance helps command discovery only.
Contracts, transitions, governed artifacts, and lifecycle truth are owned by `lib/nexus/`
and canonical `.planning/` artifacts.

Key routing rules:
- Product ideas, "is this worth building", brainstorming → invoke discover
- Scope definition, requirements framing, non-goals → invoke frame
- Architecture review, execution readiness, implementation planning → invoke plan
- Governed routing and handoff packaging → invoke handoff
- Bounded implementation execution → invoke build
- Code review, check my diff → invoke review
- QA, test the site, find bugs → invoke qa
- Ship, deploy, push, create PR → invoke ship
- Final governed verification and closure → invoke closeout

Do not auto-commit the file. After updating CLAUDE.md, tell the user the routing guidance was added and can be committed with their next repo change.

If B: run ~/.claude/skills/nexus/bin/nexus-config set routing_declined true Say "No problem. You can add routing guidance later by running nexus-config set routing_declined false and re-running any Nexus skill."

This only happens once per project. If HAS_ROUTING is yes or ROUTING_DECLINED is true, skip this entirely.

Voice

Tone: direct, concrete, sharp, never corporate, never academic. Sound like a builder, not a consultant. Name the file, the function, the command. No filler, no throat-clearing.

Writing rules: No em dashes (use commas, periods, "..."). No AI vocabulary (delve, crucial, robust, comprehensive, nuanced, etc.). Short paragraphs. End with what to do.

The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.

Contributor Mode

If _CONTRIB is true: you are in contributor mode. At the end of each major workflow step, rate your Nexus experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.

File only: Nexus tooling bugs where the input was reasonable but Nexus failed. Skip: user app bugs, network errors, auth failures on user's site.

To file: write ~/.nexus/contributor-logs/{slug}.md:

# {Title}
**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
## Repro
1. {step}
## What would make this a 10
{one sentence}
**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}

Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.

Completion Status Protocol

When completing a skill workflow, report status using one of:

• DONE — All steps completed successfully. Evidence provided for each claim.
• DONE_WITH_CONCERNS — Completed, but with issues the user should know about. List each concern.
• BLOCKED — Cannot proceed. State what is blocking and what was tried.
• NEEDS_CONTEXT — Missing information required to continue. State exactly what you need.

Escalation

It is always OK to stop and say "this is too hard for me" or "I'm not confident in this result."

Bad work is worse than no work. You will not be penalized for escalating.

• If you have attempted a task 3 times without success, STOP and escalate.
• If you are uncertain about a security-sensitive change, STOP and escalate.
• If the scope of work exceeds what you can verify, STOP and escalate.

Escalation format:

STATUS: BLOCKED | NEEDS_CONTEXT
REASON: [1-2 sentences]
ATTEMPTED: [what you tried]
RECOMMENDATION: [what the user should do next]

Plan Mode Safe Operations

When in plan mode, these operations are always allowed because they produce artifacts that inform the plan, not code changes:

• $B commands (browse: screenshots, page inspection, navigation, snapshots)
• $D commands (design: generate mockups, variants, comparison boards, iterate)
• codex exec / codex review only when the active provider route allows Codex or the user explicitly asks for Codex; in local_provider with a non-Codex primary, use the host/local subagent path instead
• Writing to ~/.nexus/ (config, review artifacts, design artifacts, learnings, eureka notes)
• Writing to the plan file (already allowed by plan mode)
• open commands for viewing generated artifacts (comparison boards, HTML previews)

These are read-only in spirit — they inspect the live site, generate visual artifacts, or get independent opinions. They do NOT modify project source files.

Plan Status Footer

When you are in plan mode and about to call ExitPlanMode:

1. Check if the plan file already has a ## NEXUS REVIEW REPORT section.
2. If it DOES — skip (a review skill already wrote a richer report).
3. If it does NOT — run this command:

```bash ~/.claude/skills/nexus/bin/nexus-review-read ```

Then write a ## NEXUS REVIEW REPORT section to the end of the plan file:

• If the output contains review entries (JSONL lines before ---CONFIG---): format the standard report table with runs/status/findings per skill, same format as the review skills use.
• If the output is NO_REVIEWS or empty: write this placeholder table:

```markdown

NEXUS REVIEW REPORT

Review	Trigger	Why	Runs	Status	Findings
CEO Review	`/plan-ceo-review`	Scope & strategy	0	—	—
Codex Review	`/codex review`	Independent 2nd opinion	0	—	—
Eng Review	`/plan-eng-review`	Architecture & tests (required)	0	—	—
Design Review	`/plan-design-review`	UI/UX gaps	0	—	—

VERDICT: NO REVIEWS YET — run `/autoplan` for full review pipeline, or individual reviews above. ```

PLAN MODE EXCEPTION — ALWAYS RUN: This writes to the plan file, which is the one file you are allowed to edit in plan mode. The plan file review report is part of the plan's living status.

/qa — Nexus Governed QA

Nexus-owned QA guidance for governed validation scope beyond code review.

Iron Laws (mandatory; non-negotiable)

These three rules apply to every /qa invocation regardless of provider, topology, or run mode. They are short and absolute on purpose — discipline that lives in qualifiers does not survive contact with the LLM at decision time. /qa runs after /review and before /ship; the verdict it writes is what /ship reads when deciding to merge.

Law 1 — QA Finding Evidence Contract

Every finding written to qa-report.md MUST carry:

1. Severity tag — P0 (broken primary flow / data loss / security regression) | P1 (broken secondary flow / important UI regression) | P2 (minor UI / non-blocking ergonomics) | P3 (cosmetic). Untagged findings are rejected.
2. Repro that ran in this turn — a step-by-step that the operator executed at finding time. The repro is verified by running it once at finding time AND once at report-write time. "Should reproduce by clicking X" is not a repro; it is a guess.
3. Evidence appropriate to category:
   • Interactive bugs (broken flows, dead controls, form failures) — screenshot before action + screenshot after action + diff snapshot. All three.
   • Static bugs (typos, layout issues, missing images) — single annotated screenshot showing the problem.
   • Console-only bugs (errors / warnings without UI break) — full console line(s) including stack frame, plus the URL where it fired.
4. No credentials — passwords, tokens, session cookies, OAuth secrets are NEVER pasted into the report. If a finding requires authenticated repro, reference the auth method (e.g., "logged in as [e-mail]") not the credential.

A finding missing severity, repro, or evidence is not a finding; it is an observation. Observations are noise; the QA report carries findings.

Law 2 — /ship-Blocking Categories Are Non-Negotiable

/qa MUST return verdict not_ready when any of these conditions hold, regardless of finding count:

1. Any P0 finding — broken primary user flow, data loss path, security regression. P0 in the report ≡ not_ready verdict. There is no "P0 but ship anyway."
2. New console error not in baseline — if baseline.json exists and the current run produces a console error not present in baseline, that is a regression. Regressions block /ship.
3. Failed health check on a primary user flow — the home / sign-in / checkout / primary CRUD page must complete its happy path without error. A failure here is not_ready even with no other findings.

Verdict ladder: ready | ready_with_findings (P1+/P2/P3 only, no console regressions, all primary flows green) | not_ready (any condition above).

/ship reads the verdict from the advisor record. If the verdict is not_ready, /ship cannot proceed; the operator routes back to /build to address blockers, then re-enters /qa.

The reason: shipping over a P0 trades user-visible breakage for release velocity. The trade is never worth it; reverts cost more than the revisit.

Law 3 — Stop After 3 Same-Root-Cause Failures

If /qa finds 3+ failures that share an apparent root cause (same module, same error class, same broken interaction pattern), stop enumerating:

1. Record the 3 findings already collected with full evidence per Law 1.
2. STOP filing variants. Do not produce a 4th, 5th, 6th finding for the same root cause.
3. Route to /investigate with the 3 collected findings as predecessor context. /investigate's 4-phase protocol (locate → analyze → hypothesize → fix) is the right tool for "what underlies this cluster."
4. /qa returns not_ready with the cluster recorded; resume after /investigate resolves the root.

Continuing past 3 same-root-cause findings is enumeration without insight. Each additional duplicate makes the report longer without making the fix faster. The 3rd repetition is a signal: the issue is not in the surface; it is in the substrate.

How to run /qa

These steps execute one /qa run. Iron Laws constrain what must be true at decision time; this workflow defines what to do in what order. Both apply.

Step 1 — Define validation scope

Read the upstream advisor record from /review. If the review verdict was not pass, /qa cannot proceed — the operator routes back to /build first. If pass, enumerate the primary user flows the run touches:

• The home / sign-in / checkout / primary CRUD pages always count as primary flows (per Law 2 #3).
• Any flow named in prd.md ## Success Criteria counts.
• Any flow surfaced by /review as design-bearing or browser-facing counts.

The scope is the union of these. A /qa run with no enumerated primary flows is not yet scoped — return to /review for a clearer handoff.

Step 2 — Run health check on each primary flow

For every primary flow, execute its happy path once. Capture before-action state, perform the canonical interaction, capture after-action state. A failure here is a P0 candidate per Law 2 #3 regardless of how minor it looks.

If the run has a baseline (baseline.json from a prior QA pass), diff console output against it as part of this step. New console errors not in baseline are Law 2 #2 regressions.

Step 3 — Enumerate findings with severity

For each observed defect, write a finding per Law 1's evidence contract:

1. Severity tag — P0 | P1 | P2 | P3. Untagged findings are rejected.
2. Repro that ran in this turn — step-by-step the operator executed, verified at finding time AND at report-write time.
3. Evidence appropriate to category:
   • Interactive: before screenshot + after screenshot + diff snapshot
   • Static: single annotated screenshot
   • Console-only: full console line(s) with stack frame + URL
4. No credentials — never paste passwords, tokens, session cookies, OAuth secrets.

A finding missing severity, repro, or evidence is an observation, not a finding. Drop it from the report or upgrade it to a finding.

Step 4 — Apply Law 2 ship-blocking gate

After findings are enumerated, evaluate the verdict ladder:

• Any P0 finding → verdict not_ready. There is no "P0 but ship anyway."
• New console error not in baseline → verdict not_ready (regression).
• Failed health check on a primary user flow → verdict not_ready.
• Otherwise, only P1+/P2/P3 findings → verdict ready_with_findings.
• No findings, all primary flows green → verdict ready.

The verdict is mechanical from the findings — it is not a judgment call.

Step 5 — Detect 3-strike cluster (per Law 3)

Scan the findings for shared root cause: same module, same error class, same broken interaction pattern. If 3+ findings cluster, STOP enumerating. Use AskUserQuestion:

"Three findings appear to share a root cause ([brief cluster description]). Should I (a) confirm cluster and route to /investigate, (b) continue gathering more variants, or (c) mark the cluster P0 and write not_ready without /investigate?"

The operator picks. If (a), record the 3 collected findings, write not_ready, route to /investigate per Law 3. If (b), continue but flag the risk in the report. If (c), the cluster is recorded as a single P0 with the 3 findings as evidence. The default expectation is (a).

Step 6 — Write qa-report.md

Compile the findings into qa-report.md per the artifact contract. At write time, re-verify each repro per Law 1 #2. A finding whose repro fails on re-verification is dropped from the report (it was a transient).

Step 7 — Write design-verification.md

For design-bearing or browser-facing runs, write design-verification.md capturing what was visually verified against intent. For non-design runs, this artifact MAY be empty but the file should still be written so /ship knows QA touched it.

Step 8 — Write status

Run the canonical command (in the Routing section below). It writes status.json with the verdict from Step 4 and any continuation artifacts. The advisor record carries the verdict; /ship reads it and refuses to proceed if not_ready.

Operator Checklist

• define governed validation scope after completed review
• record findings and ready/not-ready state explicitly
• keep provider route and runtime status explicit in canonical QA artifacts

Artifact Contract

Writes .planning/current/qa/qa-report.md, .planning/current/qa/design-verification.md, .planning/current/qa/status.json, and optionally .planning/current/qa/learning-candidates.json when QA raw output contains valid reusable learning candidates. /closeout may consume that optional artifact when assembling run learnings.

Follow-on support workflows may attach additional QA evidence without changing canonical QA state, including .planning/current/qa/perf-verification.md from /benchmark.

Routing

QA content starts only after completed review. CCB validation transport does not bypass Nexus-owned readiness decisions or advance governed execution outside Nexus.

Run:

_REPO_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
_NEXUS_ROOT="~/.claude/skills/nexus"
[ -d "$_REPO_CWD/.claude/skills/nexus" ] && _NEXUS_ROOT="$_REPO_CWD/.claude/skills/nexus"
cd "$_NEXUS_ROOT" && NEXUS_PROJECT_CWD="$_REPO_CWD" ./bin/nexus qa

Typical prompts

These are example user requests /qa handles well. The skill is invoked and produces a structured qa-report.md plus status.json with a verdict.

Prompt 1 — Standard QA after /review pass

"QA the build before we ship."

/qa walks Step 1–8. Step 1 reads the /review advisor record and enumerates primary flows from prd.md. Step 2 runs each happy path. Step 3 records findings with severity + repro + evidence. Step 4 applies the verdict ladder mechanically. If clean, status.json carries ready and /ship proceeds.

Prompt 2 — Multiple findings appearing related

"I'm seeing 5 broken-link errors across the marketing pages — should I write them all up?"

Step 5's 3-strike rule fires on the first 3 findings; the workflow stops enumerating and uses AskUserQuestion to confirm cluster routing. The default route is /investigate (Law 3) so the underlying cause gets fixed once instead of patched five times.

Prompt 3 — Found one P0

"Sign-in is broken on Safari but works on Chrome. Verdict?"

Law 2 #1: any P0 → not_ready. There is no "P0 but ship anyway." Step 4 writes not_ready mechanically. Step 6 records the finding with cross-browser repro per Law 1 #3 (interactive: before + after + diff). /ship reads the verdict and refuses to merge until the operator routes back to /build.

These prompts test that /qa produces a verdict-bearing report (not an enumeration), respects the 3-strike cluster rule, and never softens P0 → ship.

Completion Advisor

After /qa returns, prefer the runtime JSON field completion_advisor. If the host only has filesystem access, or the field is absent, fall back to .planning/current/qa/completion-advisor.json. If the runtime exited nonzero, inspect completion_context.completion_advisor from the error JSON envelope before falling back to disk. Treat that advisor as the canonical next-step contract.

Read and summarize:

• summary
• stage_outcome
• interaction_mode
• requires_user_choice
• primary_next_actions
• alternative_next_actions
• recommended_side_skills
• stop_action
• project_setup_gaps
• suppressed_surfaces
• default_action_id

If interaction_mode is summary_only, do not call AskUserQuestion. Print the advisor summary, any project_setup_gaps, and the invocation for the default_action_id if one exists.

If the session is interactive and interaction_mode is not summary_only, always use AskUserQuestion for /qa completion.

If the host cannot display AskUserQuestion, rerun /qa with --output interactive to print the same runtime-owned chooser in the terminal. Do not reconstruct choices from status.json.

If interaction_mode is recommended_choice, present:

1. recommended primary action
2. other primary actions
3. alternatives
4. recommended side skills
5. stop_action

If interaction_mode is required_choice, present only the actions emitted by the advisor.

Use each action's label and description. If an action has visibility_reason, why_this_skill, or evidence_signal, include it in the explanation so the user sees why it is showing up now.

After the user chooses an action, run the selected invocation unless the selected action is stop_action or has no invocation.

For design-bearing runs, browser-facing runs, or when the verification matrix surfaces additional support skill signals, the advisor may surface /design-review, /browse, /benchmark, /connect-chrome, /setup-browser-cookies, and /cso. Keep /ship first when QA is ready.

If QA is not ready, do not improvise. Follow the advisor back into the bounded fix cycle through /build.

If the session is non-interactive, print the advisor summary and the invocation for the default_action_id when one exists.