create-egregore 0.20.2 → 0.21.0-runtime-mvp.2

package/runtime/pi/.codex/skills/onboarding/SKILL.md

@@ -1,45 +1,40 @@
 ---
 name: onboarding
-description: 'Use for /onboarding, or when a new member''s onboarding is not yet complete — runs the deterministic VERIFY, ORIENT, INVITE, FIRST_HANDOFF welcome flow.'
+description: Use for $onboarding or incomplete first-time setup — runs the resumable welcome flow through Egregore Runtime.
 ---
 
-<!-- generated-by: bin/codex-sync-skills.sh -->
-
-# Egregore onboarding Adapter
-
-This is fallback coverage for a long-tail Egregore workflow that has not been
-ported to a hand-written Codex-native skill yet.
-
-Use the project shell and filesystem directly. Do not invoke Claude Code
-commands. Translate interactive choices to structured Codex question tooling
-when it is available; otherwise render compact numbered choices with an
-`Other:` option and wait for the user.
-
-## Structured UX parity
-
-This workflow has a Claude skill with user-visible structured output. After
-reading `.claude/skills/onboarding/SKILL.md`, reproduce the same visible UX in Codex:
-
-- Preserve TUI boxes, markdown tables, rich cards, browser artifact rendering,
-  exact confirmation blocks, and "no preamble" rules from the source skill.
-- Use the source skill's frame width, section order, labels, status footer,
-  and examples as the contract for the final response.
-- Never replace a required box/table/card/artifact view with a prose summary
-  unless the user explicitly asks for a summary.
-- When the source says to output a TUI box directly, paste that box as the
-  visible response, preferably in a `text` fenced block.
-- Never show raw JSON, raw command output, or unformatted script output when
-  the source skill requires formatted status or rendered output.
-
-1. Read `.claude/skills/onboarding/SKILL.md` for the workflow details.
-2. Run the referenced `bin/` scripts directly from Codex.
-3. Treat graph and publish steps as best-effort unless that workflow explicitly
-   says they are required.
-4. For every external notification, follow
-   `.claude/context/notification-consent.md`: plan without sending, then show
-   a separate exact Send / Edit / Cancel checkpoint. Never infer notification
-   consent from the workflow request or a batch approval.
-5. Keep local-mode behavior filesystem-first and avoid graph or notification
-   calls when `egregore.json` declares `"mode": "local"`.
-6. Never call the deprecated `egregore-handoff` CLI for Egregore project
-   handoffs.
+# Egregore onboarding
+
+Start or resume with one bounded command:
+
+```bash
+ONBOARDING_JSON=$(bash bin/onboarding.sh status)
+```
+
+The Runtime owns state migration, ActorContext authorization, Local/Connected
+detection, identity reconciliation, canonical profile witnesses, and Git
+provenance. `AccountIdentity`, `ActorIdentity`, and `OrgMembership` remain
+separate; GitHub is only a provider/transport alias. Do not edit state or
+identity files or call APIs, graph, Git, or notification transports directly.
+
+Preserve the Claude source skill's visible flow:
+
+1. Render its exact Insight block and ask the member's preferred name unless
+   the receipt says the installer already captured it. Record it with
+   `bash bin/onboarding.sh set-name "$CHOSEN_NAME"`.
+2. Founders may invite via the `invite` skill or skip, then record the answer
+   with `bash bin/onboarding.sh record-invite invited|skipped`. Joiners are
+   never asked to invite and use `skipped`.
+3. Teach save and handoff in two lines, then ask what they are working on and
+   use the ordinary branch skill.
+4. Joiners fast-track with `bash bin/onboarding.sh complete`. Creators complete
+   only after their first ordinary handoff, using the same command.
+
+If already complete, do not repeat setup. If only role is missing, ask only
+that and run `bash bin/onboarding.sh set-role "$ROLE"`. A missing profile
+witness keeps onboarding resumable. Render command receipts without raw JSON
+or internal IDs.
+
+Inviting never authorizes a notification. Any invite message requires its own
+fresh exact notification plan and **Send / Edit / Cancel** approval; never
+fall back to a group.

package/runtime/pi/.codex/skills/pull/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pull
-description: 'Use for /pull when you need to sync the current branch and shared memory without also viewing activity (/activity auto-syncs already).'
+description: 'Use for /pull when you need to sync the current branch and shared memory. Activity and dashboard are read-only and never sync repositories.'
 ---
 
 <!-- generated-by: bin/codex-sync-skills.sh -->

package/runtime/pi/.codex/skills/quest/SKILL.md

@@ -1,80 +1,41 @@
 ---
 name: quest
-description: Manage Egregore quests from Codex when the user invokes /quest or $quest, or asks to manage quests, using memory-first files and optional connected-mode graph updates.
+description: Manage shared open-ended Egregore quests through the canonical Runtime lifecycle. Use for $quest, listing or opening quests, starting an exploration, contributing, prioritizing, pausing, or completing a quest.
 ---
 
 # Egregore Quest
 
-Native Codex Egregore skill. Quests are shared, open-ended explorations stored
-under `memory/quests/`.
+Use `bin/quest.sh` as the only quest lifecycle adapter. Canonical Markdown/Git
+is authoritative in Local and Connected modes; retrieval indexes, dashboards,
+and graph records are optional rebuildable projections.
 
-## Flow
+## Route
 
-1. Run `bin/agent.sh sync`.
-2. Detect mode from `egregore.json` `mode`, defaulting to `connected`.
-3. Dispatch from the user request:
-   - no argument: list active and paused quests from `memory/quests/*.md`.
-   - name or slug: show quest details from the markdown file.
-   - `new`: create a quest.
-   - `contribute`: append a contribution entry.
-   - `prioritize`: set `priority` to `0`, `1`, `2`, or `3`.
-   - `pause`: set `status: paused`.
-   - `complete`: set `status: completed` and record an outcome.
-4. Filesystem writes are canonical. Quest files use frontmatter:
+- empty: `bash bin/quest.sh list`
+- `all`: `bash bin/quest.sh list --all`
+- name: resolve from one list snapshot, then `bash bin/quest.sh show <slug>`
+- `new`: collect title, open question, and optional slug/projects/threads, then
+  make one `new` call
+- `contribute`, `prioritize`, `pause`, `complete`: resolve once, then perform
+  one explicit transition by stable slug
 
-```yaml
----
-title: Example Quest
-slug: example-quest
-status: active
-projects: []
-started: YYYY-MM-DD
-started_by: handle
-priority: 0
-completed:
----
-```
-
-5. Update `memory/quests/index.md` after create, status changes, and priority
-   changes.
-6. Commit and push memory immediately:
+Commands:
 
 ```bash
-git -C memory add quests
-git -C memory commit -m "quest: $SLUG $ACTION" --quiet
-git -C memory push origin main --quiet
+bash bin/quest.sh new --title "<title>" --question "<question>" \
+  [--slug "<slug>"] [--project "<project>"]... [--thread "<thread>"]...
+bash bin/quest.sh contribute "<slug>" "<contribution>"
+bash bin/quest.sh prioritize "<slug>" "<none|low|medium|high>"
+bash bin/quest.sh pause "<slug>"
+bash bin/quest.sh complete "<slug>" --outcome "<outcome>"
 ```
 
-7. In connected mode only, mirror changes best-effort with `bin/graph.sh`.
-   For each named person, follow `.claude/context/notification-consent.md`:
-   create a direct-message plan, then show a separate exact Send / Edit /
-   Cancel checkpoint. Selecting quest participants is not notification
-   consent, and approvals cannot be batched across recipients. If planning or
-   dispatch fails, report that the quest was saved to memory and continue.
-
-## Interaction
-
-Use structured Codex question tooling when available for new quest fields and
-status confirmations. Otherwise ask one short numbered question at a time with
-an `Other:` option.
-
-## Output
-
-Structured UX parity is required:
-
-- `/quest` list mode renders the active quest table:
-  `| Quest | Project | Artifacts | Contributors |`, followed by paused quest
-  state and entry-point hints.
-- `/quest <name>` detail mode renders the same sectioned view as Egregore:
-  title rule, status, projects, started metadata, question, threads,
-  artifacts, todos when available, contributors, and entry points.
-- Create/update routes use compact structured confirmations with the quest
-  file path and memory push state. Do not substitute a loose prose summary.
-- In local mode, omit graph/notification wording while preserving the same
-  list/detail layout.
-
-## Rules
+Suppress raw JSON and render a compact list/detail/receipt. Completion requires
+an explicit outcome. Never infer completion from age, inactivity, todos, or
+graph state.
 
-- Do not use graph or notification calls in local mode.
-- Do not let graph failure block a filesystem quest update.
-- Do not use Claude Code commands.
+Do not edit files or run Git, QMD, Neo4j, Supabase, publishing, or notification
+mechanics directly. The adapter resolves `ActorContext`, authorizes before
+content access, performs one canonical writeback, and updates disposable
+projections afterward. Surface partial-write warnings without retrying the
+whole mutation. Notification consent is always a later, separate action.

package/runtime/pi/.codex/skills/reflect/SKILL.md

@@ -1,45 +1,31 @@
 ---
 name: reflect
-description: 'Use when the user says ''we decided'', ''I realized'', or ''that''s a pattern'' — captures decisions, findings, or patterns in shared memory. Not a private half-baked thought (/note) or cross-referencing (/deep-reflect).'
+description: "Use when the user says 'we decided', 'I realized', or 'that's a pattern' — captures a share-ready decision, finding, or pattern in canonical organizational memory. Use $note for private thoughts and $archive for AI-steering techniques."
 ---
 
-<!-- generated-by: bin/codex-sync-skills.sh -->
+# Reflect
 
-# Egregore reflect Adapter
+Classify settled insights as `decision`, `finding`, or `pattern` (maximum three;
+default ambiguous material to `finding`). Reuse attached
+`EGREGORE_ORG_CONTEXT_V1`; when sufficient, neither search nor reopen. For a
+named gap, make one `bash bin/search.sh query` call and open only the missing
+canonical evidence through the same adapter.
 
-This is fallback coverage for a long-tail Egregore workflow that has not been
-ported to a hand-written Codex-native skill yet.
+Show title, content, context, rationale, topics, workstream, and any explicit
+relations/supersession. Wait for acceptance or edits. Render each accepted body
+to a temporary file, then call exactly once per artifact:
 
-Use the project shell and filesystem directly. Do not invoke Claude Code
-commands. Translate interactive choices to structured Codex question tooling
-when it is available; otherwise render compact numbered choices with an
-`Other:` option and wait for the user.
+```bash
+bash bin/knowledge.sh create --type "{type}" --title "{title}" \
+  --input "$TMP_ARTIFACT" --topic "{topic}" --workstream "{workstream}"
+```
 
-## Structured UX parity
+Use repeated `--topic`, `--relationship "RELATION:TARGET"`, and `--supersedes`
+only when known. This Runtime command owns ActorContext authorization, stable
+typed identity/provenance, canonical Markdown, Git provenance, retrieval
+refresh, background embedding, and content-free telemetry.
 
-This workflow has a Claude skill with user-visible structured output. After
-reading `.claude/skills/reflect/SKILL.md`, reproduce the same visible UX in Codex:
-
-- Preserve TUI boxes, markdown tables, rich cards, browser artifact rendering,
-  exact confirmation blocks, and "no preamble" rules from the source skill.
-- Use the source skill's frame width, section order, labels, status footer,
-  and examples as the contract for the final response.
-- Never replace a required box/table/card/artifact view with a prose summary
-  unless the user explicitly asks for a summary.
-- When the source says to output a TUI box directly, paste that box as the
-  visible response, preferably in a `text` fenced block.
-- Never show raw JSON, raw command output, or unformatted script output when
-  the source skill requires formatted status or rendered output.
-
-1. Read `.claude/skills/reflect/SKILL.md` for the workflow details.
-2. Run the referenced `bin/` scripts directly from Codex.
-3. Treat graph and publish steps as best-effort unless that workflow explicitly
-   says they are required.
-4. For every external notification, follow
-   `.claude/context/notification-consent.md`: plan without sending, then show
-   a separate exact Send / Edit / Cancel checkpoint. Never infer notification
-   consent from the workflow request or a batch approval.
-5. Keep local-mode behavior filesystem-first and avoid graph or notification
-   calls when `egregore.json` declares `"mode": "local"`.
-6. Never call the deprecated `egregore-handoff` CLI for Egregore project
-   handoffs.
+Do not call Git, QMD, graph, control-plane storage, telemetry, publishing,
+sharing, or notification mechanics directly. Graph is optional and advisory.
+Publishing, external sharing, and notification require separate permission and
+explicit consent. Report the canonical path and writeback status.

package/runtime/pi/.codex/skills/save/SKILL.md

@@ -46,8 +46,8 @@ esac
    `capability-distribution.json` exists:
 
 ```bash
-node bin/capability-distribution.mjs validate --root .
-node bin/capability-distribution.mjs changes --root . --base "origin/$BASE" --json
+bash bin/node-run.sh bin/capability-distribution.mjs validate --root .
+bash bin/node-run.sh bin/capability-distribution.mjs changes --root . --base "origin/$BASE" --json
 ```
 
    Inspect the diff as well as the receipt. Ask when this work introduces a new

package/runtime/pi/.codex/skills/telemetry/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: telemetry
-description: 'Manage your own telemetry settings — check status, opt in/out, view or clear the buffered events. Use for /telemetry, ''turn off telemetry'', or ''what data do you collect''.'
+description: 'Manage local-first telemetry — status, inspect, export, opt in/out, clear, or explicitly share a disclosed dataset. Use for /telemetry, ''turn off telemetry'', or ''what data do you collect''.'
 ---
 
 <!-- generated-by: bin/codex-sync-skills.sh -->

package/runtime/pi/.codex/skills/test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test
-description: 'Validate changes before /save — static analysis plus live Cypher validation against the graph, rendered as a pass/fail gate. Use for /test or ''test my changes''.'
+description: 'Run Egregore''s fast static, Runtime-contract, and targeted automated test gate before save. Graph validation is explicit and never part of the Local default.'
 ---
 
 <!-- generated-by: bin/codex-sync-skills.sh -->

package/runtime/pi/.codex/skills/tutorial/SKILL.md

@@ -1,45 +1,44 @@
 ---
 name: tutorial
-description: 'Interactive walkthrough of Egregore''s core loop — /activity, /reflect, and /quest or /add — with adaptive questions and real artifacts. Use for /tutorial or ''walk me through Egregore''.'
+description: "Interactive walkthrough of Egregore's Local core loop — activity, reflection, and a quest — using adaptive questions and real Runtime-backed artifacts. Use for 'tutorial', 'walk me through Egregore', or 'show me how this works'."
 ---
 
-<!-- generated-by: bin/codex-sync-skills.sh -->
-
-# Egregore tutorial Adapter
-
-This is fallback coverage for a long-tail Egregore workflow that has not been
-ported to a hand-written Codex-native skill yet.
-
-Use the project shell and filesystem directly. Do not invoke Claude Code
-commands. Translate interactive choices to structured Codex question tooling
-when it is available; otherwise render compact numbered choices with an
-`Other:` option and wait for the user.
-
-## Structured UX parity
-
-This workflow has a Claude skill with user-visible structured output. After
-reading `.claude/skills/tutorial/SKILL.md`, reproduce the same visible UX in Codex:
-
-- Preserve TUI boxes, markdown tables, rich cards, browser artifact rendering,
-  exact confirmation blocks, and "no preamble" rules from the source skill.
-- Use the source skill's frame width, section order, labels, status footer,
-  and examples as the contract for the final response.
-- Never replace a required box/table/card/artifact view with a prose summary
-  unless the user explicitly asks for a summary.
-- When the source says to output a TUI box directly, paste that box as the
-  visible response, preferably in a `text` fenced block.
-- Never show raw JSON, raw command output, or unformatted script output when
-  the source skill requires formatted status or rendered output.
-
-1. Read `.claude/skills/tutorial/SKILL.md` for the workflow details.
-2. Run the referenced `bin/` scripts directly from Codex.
-3. Treat graph and publish steps as best-effort unless that workflow explicitly
-   says they are required.
-4. For every external notification, follow
-   `.claude/context/notification-consent.md`: plan without sending, then show
-   a separate exact Send / Edit / Cancel checkpoint. Never infer notification
-   consent from the workflow request or a batch approval.
-5. Keep local-mode behavior filesystem-first and avoid graph or notification
-   calls when `egregore.json` declares `"mode": "local"`.
-6. Never call the deprecated `egregore-handoff` CLI for Egregore project
-   handoffs.
+# Tutorial
+
+Guide one conversational orient → capture → connect → close loop. Reuse
+onboarding answers and attached `EGREGORE_ORG_CONTEXT_V1`; do not repeat
+retrieval. Resume tutorial-only local state when present.
+
+1. **Orient:** ask only missing domain/stage questions. Fetch exactly one
+   `bin/activity-data.sh` snapshot and render it without a temporary file:
+
+```bash
+bash bin/activity-data.sh 2>/dev/null \
+  | bash bin/node-run.sh bin/codex-skill-render.mjs activity-card -
+```
+2. **Capture:** ask two adaptive questions about the user's real work. Infer a
+   decision, finding, or pattern; preview and explicitly confirm it. Render one
+   body to a temporary file, then call exactly once:
+
+```bash
+bash bin/knowledge.sh create --type "{type}" --title "{title}" \
+  --input "$TMP_ARTIFACT" --topic tutorial-generated \
+  --topic "{topic}" --workstream tutorial
+```
+
+3. **Connect:** ask for the bigger open question, success condition, and up to
+   three initial threads. If accepted, create one quest:
+
+```bash
+bash bin/quest.sh new --title "{title}" --question "{question}" \
+  --project tutorial-generated --thread "{thread}"
+```
+
+4. **Close:** show accepted canonical paths, ask one feedback question, keep feedback local
+   unless separately promoted, mark complete, and end exactly:
+   **What are you working on?**
+
+Do not call Git, QMD, graph, control-plane storage, telemetry, publishing,
+sharing, or notification mechanics directly. One Runtime call owns each
+accepted write. Adding people or external effects requires separate permission
+and explicit consent. Canonical Markdown/Git wins over projections.