discover

name	discover
preamble-tier	1
version	0.1.0
description	Canonical Nexus discovery command. Writes repo-visible discovery artifacts and stage status through Nexus-owned normalization and governance. Use when the user says "I want to explore X", "we should look into Y", "I'm not sure what we should build for Z", or when the problem is still vague and needs clarification before /frame can scope it. (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.

/discover — Nexus Discovery

Nexus-owned discovery guidance for clarifying the problem before framing.

Iron Laws (mandatory; non-negotiable)

These three rules apply to every /discover 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. /discover is the entry edge of the lifecycle; ambiguity here propagates straight through to the user.

Law 1 — What /discover Is NOT

/discover rejects these patterns at entry. If the work is drifting into any of them, stop and reframe:

1. Not a feature spec — discovery does not produce "build X with Y fields and Z button." That is /plan's output. Discovery output is a problem statement; the solution comes after /frame confirms scope.
2. Not user testing — discovery is not "have users click on prototypes and tell us what they think." It is upstream of any artifact to test. If the work is testing something, it is not yet discovery.
3. Not a substitute for shipping — discovery does not replace learning from a shipped change. If a small slice can be shipped to validate the hypothesis, route to pol-probe (lightweight validation) instead of expanding discovery scope.
4. Not single-stakeholder framing — discovery from one person's view of the problem is biased framing. The artifact must reflect ≥2 perspectives (user + owner, owner + ops, etc.); single-source discovery is captured but flagged as a known limitation.
5. Not solutioning in disguise — "we should add X" is a solution. "Users currently fail at Y because Z" is discovery. If the brief reads like a feature list, discovery hasn't started yet.

A /discover artifact that reads like any of these is a category error. Re-enter discovery rather than passing the artifact to /frame.

Law 2 — Minimum Signal Bar Before /frame

docs/product/idea-brief.md MUST carry the following before /discover writes status.json with verdict ready:

1. Named user segment — not "users." A specific segment with a name (e.g., "operators running multi-provider Nexus on macOS"). The name does not have to be a customer; it has to be specific enough that ≠ "everyone."
2. Observed pain with cost — what the named user fails at and what that failure costs (time, money, churn, broken trust). "Users are frustrated" fails; "operators run /build, hit a 3-strike loop, and abandon the session 18% of the time per session-archive logs" passes.
3. ≥2 evidence sources — at least two distinct sources informed this discovery. Sources count as: user interviews, support tickets, metrics, prior PRDs, market signals, internal usage logs, customer email threads. Two sources of the same type (e.g., two interview transcripts) count as two; same source quoted twice does not.
4. Hypothesis hint — a one-paragraph version of the "If/Then/Because" hypothesis (per /frame Law 2) that /frame will sharpen. The hint may be incomplete; the framing pass refines it. But discovery without a hypothesis hint is observation, not direction.
5. Open questions list — explicit questions for /frame to answer, ≥3 items. "What's the success metric?", "Which segment ships first?", "What's the rollback plan?" are typical. Empty open-questions sections mean discovery overclaimed.

If any of the five fail, /discover returns not_ready. /frame reads the verdict from the advisor record. If not_ready, /frame cannot proceed.

Discovery-from-vibes is a real failure mode. The signal bar exists because two interviews + one customer email is cheaper than three weeks of /build based on guessed framing.

Law 3 — Look Inward Before Look Outward

idea-brief.md MUST contain two clearly separated sections, in this order:

1. Look Inward — what the team currently believes, before gathering evidence. Captures team assumptions, prior framings, the hypothesis the team is bringing in. This section is written FIRST so the team's prior is on the record.
2. Look Outward — what evidence was gathered (interviews, tickets, metrics, etc.) and what it actually said. Cite each piece of evidence to its source per Law 2.

Without Look Inward, the team cannot tell what its prior was — and cannot tell whether its evidence collection was confirming or challenging that prior. That is the trap of confirmation-only discovery: the team interviews until interviews agree with what the team already thought.

The brief MAY end with a brief Reframe section noting where Look Outward changed Look Inward — what the team thought going in vs. what it concluded. The Reframe is the receipt that discovery happened.

The reason: a discovery brief that does not record the team's prior is unfalsifiable as a discovery output. There is no way to tell whether the brief reflects what users said or what the team wanted users to say.

How to run /discover

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

Step 1 — Read upstream context

If a prior closeout produced next-run-bootstrap.json or RETRO-CONTINUITY.md for this run, read them first. They carry seeded discovery context and prior open questions; ignoring them duplicates work the team already did.

If no prior closeout context exists, this is a fresh discovery run — proceed to Step 2.

Step 2 — Capture Look Inward

Before gathering any evidence, write the team's current beliefs into a draft idea-brief.md ## Look Inward section (per Law 3). Capture:

• The problem the team thinks exists
• The user segment the team thinks is affected
• The hypothesis the team is bringing in
• Any prior framings or assumptions the team is operating under

This step exists so confirmation bias is on the record. Skip it and Law 3 fails.

Step 3 — Detect anti-patterns early

If the captured Look Inward already reads like any of Law 1's 5 anti-patterns (feature spec, user testing, substitute-for-shipping, single-stakeholder, solutioning in disguise), STOP. Use AskUserQuestion:

"The current Look Inward reads like a [feature spec | solutioning | etc.]. Should I (a) reframe as a problem statement, (b) route to pol-probe for lightweight validation, or (c) continue and flag in the brief?"

The operator picks; record the choice in the brief.

Step 4 — Gather Look Outward evidence

Per Law 2 the brief needs ≥2 distinct evidence sources. Sources to consider:

• User interviews (transcripts or notes)
• Support tickets matching the problem space
• Usage metrics or telemetry
• Prior PRDs or design docs
• Market signals (competitor moves, public commentary)
• Customer email threads
• Internal usage observations

Cite each piece of evidence to its source. Two interview transcripts count as two sources; the same email quoted twice does not.

Step 5 — Synthesize hypothesis hint

From Look Outward findings, draft a one-paragraph "If/Then/Because" hint per Law 2 #4. This is not the final hypothesis — /frame Law 2 sharpens it. The hint just commits to a direction the framing pass can refine.

Step 6 — Enumerate open questions

List ≥3 explicit questions for /frame to answer (per Law 2 #5). Examples:

• "What's the falsifiable success metric?"
• "Which user segment ships first?"
• "What's the rollback plan if hypothesis fails?"

If you can't enumerate three, the discovery has overclaimed — return to Step 4 and gather more.

Step 7 — Write Reframe section (optional but recommended)

If Look Outward changed Look Inward in any way, write a brief ## Reframe section noting:

• What the team thought going in
• What it concluded after evidence
• Why the change matters

The Reframe is the receipt that discovery actually happened.

Step 8 — Verify all 5 Law 2 checks pass

Before writing status.json, verify the brief has:

1. Named user segment (not "users")
2. Observed pain with concrete cost
3. ≥2 distinct evidence sources cited
4. Hypothesis hint
5. ≥3 open questions

If any fail, return to the relevant step. If all pass, proceed to Step 9.

Step 9 — Write status

Run the canonical command (in the Routing section below). It writes idea-brief.md, status.json, and any continuation artifacts. The advisor record carries the verdict; /frame reads it.

Operator Checklist

• capture goals
• capture constraints
• record open questions

Artifact Contract

Writes docs/product/idea-brief.md, .planning/current/discover/status.json, and, for fresh runs seeded from archived closeout, .planning/current/discover/NEXT-RUN.md, .planning/current/discover/next-run-bootstrap.json, .planning/current/discover/retro-continuity.json, .planning/current/discover/RETRO-CONTINUITY.md, .planning/current/discover/session-continuation-advice.json, and .planning/current/discover/SESSION-CONTINUATION.md.

Routing

Advance to /frame only after Nexus writes the discovery artifacts.

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 discover

Typical prompts

These are example user requests /discover handles well. The skill is invoked and produces a structured idea-brief.md plus status.json.

Prompt 1 — Vague feature idea

"I think Nexus should have some kind of telemetry, but I don't really know what shape."

/discover walks Step 1–9. Look Inward captures the team's prior ("telemetry would help with X"). Look Outward gathers evidence (existing logs? competitor approaches? user requests?). Hypothesis hint emerges. Open questions enumerate what /frame must decide. Brief returns ready if all 5 Law 2 checks pass.

Prompt 2 — Reactive problem framing

"Multiple users are reporting /build feels broken when 3-strike fires; I want to understand why before we patch."

Step 1 reads any prior LEARNINGS.md for relevant context. Step 2 captures team's current theory. Step 3 detects whether the prompt is already a solution (it isn't — "understand why" is discovery-shaped). Step 4 gathers actual session logs, prior reports. Step 5 produces hypothesis hint. The brief frames the problem rather than proposing fixes.

Prompt 3 — Strategic exploration

"Should Nexus expand beyond CCB transport? What would that look like?"

Step 2 captures team's strategic prior. Step 4 gathers competitive landscape, current architectural constraints, prior strategic docs. Hypothesis hint commits to one direction (e.g., "If we add X transport, then Y users will Z because evidence W"). Open questions are aggressive — multiple items the team can't yet answer.

These prompts test that /discover produces structured discovery output, not feature specs or implementation plans (Iron Law 1's anti-patterns).

Completion Advisor

After /discover 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/discover/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
• 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 /discover completion.

If the host cannot display AskUserQuestion, rerun /discover 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.

/discover normally has a single canonical continuation into /frame. The advisor may also surface /pol-probe as a side skill when Iron Law 1's anti-patterns suggest lightweight validation is the right next move (e.g., the discovery output is starting to read like solutioning rather than problem framing). For genuinely strategic discoveries that need additional sharpening, the advisor may recommend re-entering /discover with a tighter hypothesis hint before /frame.

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