@harness-lab/cli 0.3.2 → 0.4.0

package/README.md

@@ -74,12 +74,16 @@ harness version
 harness --help
 ```
 
-Install the portable workshop skill bundle into your current repo for Codex/pi discovery:
+## Participant Quick Start
+
+If you are a workshop participant, this is the only command you need:
 
 ```bash
 harness skill install
 ```
 
+This installs the workshop skill into your current repo. After install, open Codex or pi in the same repo and run `$workshop commands` to get started. You do not need any of the facilitator commands below.
+
 Optional explicit target:
 
 ```bash
@@ -93,6 +97,12 @@ Treat the installed `workshop` skill as the first participant entrypoint. It sho
 
 Treat `.agents/skills/harness-lab-workshop` as generated workshop bundle content. The canonical authored source remains in this repository under `workshop-skill/`, `workshop-blueprint/`, selected `docs/`, and selected `materials/`.
 
+---
+
+## Facilitator Commands
+
+Everything below this line is for facilitators managing workshop instances.
+
 Default device/browser login:
 
 ```bash

package/assets/workshop-bundle/SKILL.md

@@ -3,8 +3,9 @@ name: workshop
 description: >
   Participant-facing skill for the Harness Lab workshop. Supports the
   `workshop` skill interface for setup, briefs, challenges, reference
-  materials, recap, and facilitator actions using live dashboard data when
-  available and local fallback content otherwise.
+  materials, recap, and repo analysis using live dashboard data when
+  available and local fallback content otherwise. Facilitator commands
+  live in SKILL-facilitator.md and load only after facilitator login.
 allowed-tools:
   - Read
   - Grep
@@ -43,7 +44,6 @@ Command semantics stay in English. Resolve the response language in this order:
 3. If there is no clear live or user-language signal, default bundled fallback delivery to English (`en`).
 
 Additional rules:
-- facilitator-control commands are operational rather than room-facing delivery, so prefer the user's current language unless the facilitator explicitly asks for another reviewed locale or you are quoting workshop content
 - the authored language of a supporting doc does not decide the reply language by itself
 - if the requested locale has no reviewed variant, fall back to English and say so explicitly
 - do not let a Czech-authored fallback file force a Czech answer when the resolved response locale is English
@@ -71,7 +71,8 @@ Rule:
 - runtime edits do not imply blueprint edits; reusable changes belong back in the repo deliberately
 - prefer workshop `contentLang` for participant-facing responses in live mode
 - if there is no live workshop context, resolve the fallback locale using the Language Resolution rules above and say when the answer is fallback content rather than live workshop state
-- for bundled fallback docs, resolve `workshop-skill/locales/<locale>/...` first; if a reviewed localized doc does not exist yet, fall back to English and say so explicitly
+- for bundled fallback docs, resolve `workshop-skill/locales/<locale>/...` first; if a reviewed localized doc does not exist yet, fall back to `workshop-skill/locales/en/...` and say so explicitly
+- the root-level files in `workshop-skill/` (e.g. `workshop-skill/reference.md`) are the Czech-authored source. When the resolved locale is English, always prefer `workshop-skill/locales/en/` over the Czech root files. Never serve a Czech root file to an English-resolved session.
 - do not translate workshop copy ad hoc when a reviewed locale exists in the repo or bundle
 
 ## Commands
@@ -139,7 +140,7 @@ Show:
 ### `workshop help`
 
 Give phase-aware coaching. Examples:
-- during Build Phase 1: remind the team to get a short `AGENTS.md`, a plan, commands, one executable check, and a reviewed output in place
+- during Build Phase 1: remind the team to get a short `AGENTS.md`, a plan, commands, one executable check, and a reviewed output in place. Also include this provocation: "Zkuste toto: dejte agentovi úkol bez omezení a sledujte, co si vybere. Pak porovnejte výsledek se čtyřmi prvky dobrého úkolu (Goal / Context / Constraints / Done When). Co chybělo?"
 - during the continuation shift: tell the team to read before editing and to preserve evidence of what they changed
 - when the team is letting the agent work with more autonomy: push them toward tests, tracer bullets, or another executable check
 - for UI work: recommend `agent exploration -> Playwright regression -> human review` as the safe default workflow
@@ -169,15 +170,6 @@ Return a short participant-facing menu of the skill surface:
 - the shortest recommended path for a new participant
 Use `workshop-skill/locales/<locale>/commands.md` when present, otherwise fall back to `workshop-skill/commands.md`.
 
-### `workshop closing`
-
-Prepare Ondrej's closing synthesis by using:
-- sprint checkpoints from the dashboard
-- monitoring summary
-- W³ commitments or closing notes
-Use `workshop-skill/closing-skill.md`.
-Treat this as facilitator-facing. Do not proactively surface it to participants during normal workshop help.
-
 ### `workshop reference`
 
 Return the workshop reference card from `workshop-skill/locales/<locale>/reference.md` when present, otherwise fall back to `workshop-skill/reference.md`.
@@ -204,136 +196,6 @@ Use this when the participant asks for further reading, public examples, optiona
 Return the follow-up package from `workshop-skill/locales/<locale>/follow-up-package.md` when present, otherwise `workshop-skill/follow-up-package.md`.
 Use this when the participant asks what to do after the workshop, what to revisit tomorrow, or what materials to keep using next week.
 
-### `workshop facilitator login`
-
-Authenticate as a facilitator through the `harness` CLI privileged path.
-The skill should ask the facilitator to complete CLI login/bootstrap if needed, then use the CLI-backed session for subsequent commands.
-This is a facilitator-only command — do not surface to participants.
-
-### `workshop facilitator status`
-
-Show the current instance state, agenda phase, facilitator list, and team count.
-Requires active facilitator session.
-If a local current instance is selected, prefer that target over deployment-default status.
-When an agent needs machine-readable output, prefer `harness --json workshop status`.
-
-### `workshop facilitator current-instance`
-
-Show the locally selected facilitator target, where it came from, and the resolved instance record.
-Prefer invoking `harness workshop current-instance`.
-Use this to confirm the CLI target before update, reset, prepare, remove, or phase operations.
-
-### `workshop facilitator select-instance <instance-id>`
-
-Persist a facilitator-local current target for later workshop commands.
-Prefer invoking `harness workshop select-instance <instance-id>`.
-Use `harness workshop select-instance --clear` to remove the stored selection.
-
-### `workshop facilitator list-instances`
-
-List the facilitator-visible workshop instance registry.
-Prefer invoking `harness workshop list-instances` over raw API scripts or local session-file inspection.
-Use this when the facilitator needs to discover what currently exists on a shared dashboard before choosing an explicit instance for reset, update, or agenda work.
-When an agent needs strict parsing, prefer `harness --json workshop list-instances`.
-
-### `workshop facilitator show-instance <instance-id>`
-
-Inspect one explicit workshop instance.
-Prefer invoking `harness workshop show-instance <instance-id>` over raw API scripts.
-Use this when the facilitator needs the full record for one instance rather than the deployment-default runtime status returned by `workshop facilitator status`.
-If a current instance is already selected, the CLI may omit `<instance-id>` and use the stored target.
-
-### `workshop facilitator participant-access`
-
-Inspect or rotate the shared participant event code for the current workshop instance.
-Prefer invoking `harness --json workshop participant-access` for inspection and `harness --json workshop participant-access --rotate` to issue a fresh code.
-If the current raw code is no longer recoverable from the hash-only runtime store, issue a new code instead of guessing.
-
-### `workshop facilitator grant <email> <role>`
-
-Grant a Neon Auth user access to the current workshop instance.
-Roles: owner, operator, observer. Requires `owner` role.
-
-### `workshop facilitator revoke <email>`
-
-Revoke a facilitator's access to the current instance. Requires `owner` role.
-
-### `workshop facilitator create-instance`
-
-Create a new workshop instance from a template. Requires facilitator session.
-Prefer invoking `harness workshop create-instance` over raw API scripts.
-
-The skill should support rich event metadata, not just id and city:
-- `id`
-- `templateId`
-- `contentLang`
-- `eventTitle`
-- `city`
-- `dateRange`
-- `venueName`
-- `roomName`
-- `addressLine`
-- `locationDetails`
-- `facilitatorLabel`
-
-### `workshop facilitator update-instance <instance-id>`
-
-Update event metadata for an existing workshop instance. Requires facilitator session.
-Prefer invoking `harness workshop update-instance` over raw API scripts.
-Use this when the facilitator wants to correct or refine date, venue, room, address, or event title without resetting the instance.
-Support `contentLang` changes explicitly so facilitators can choose workshop delivery language per instance without changing admin UI language.
-
-Facilitator discovery rule:
-- for routine discovery, use `harness workshop list-instances` and `harness workshop show-instance`
-- for repeated work on one live workshop, use `harness workshop select-instance <instance-id>` and `harness workshop current-instance`
-- do not read local CLI session files or improvise authenticated `node -e` fetch scripts unless you are diagnosing the CLI itself
-
-### `workshop facilitator reset-instance <instance-id>`
-
-Reset one existing workshop instance from the selected blueprint template. Requires facilitator session.
-Prefer invoking `harness workshop reset-instance` over raw API scripts.
-Use this when the facilitator wants fresh canonical agenda, runner, and presenter content for a live instance and accepts that local runtime state will be reinitialized.
-If a current instance is already selected, the CLI may omit `<instance-id>` and use the stored target.
-
-### `workshop facilitator remove-instance`
-
-Remove a workshop instance from the active list without deleting its archive history. Requires facilitator session.
-Prefer invoking `harness workshop remove-instance`.
-If a current instance is already selected, the CLI may omit `<instance-id>` and use the stored target.
-
-### `workshop facilitator prepare`
-
-Set the current instance to `prepared` state. Verify event code is ready.
-Prefer invoking `harness workshop prepare`.
-If a current instance is already selected, the CLI may omit `<instance-id>` and use the stored target.
-
-### `workshop facilitator agenda`
-
-Inspect and edit the local agenda copy for one workshop instance. Requires facilitator session.
-
-### `workshop facilitator scenes`
-
-Inspect and edit presenter scenes for one workshop instance. This includes listing scenes for an agenda item, creating a new scene, editing content, changing default scene, reordering scenes, and enabling or hiding scenes. Requires facilitator session.
-
-Rules for rich scenes:
-- keep scenes agenda-linked and room-facing rather than inventing a freeform slide deck
-- prefer one dominant voice per scene and one main idea per scene
-- use reviewed local blueprint assets for reusable visuals instead of ad hoc remote image URLs
-- treat runtime scene edits as instance-local until a maintainer deliberately publishes them back into the repo
-- when richer scene authoring or promotion is involved, follow `docs/presenter-rich-scene-authoring.md`
-
-### `workshop facilitator archive`
-
-Archive the current workshop instance with optional notes.
-
-### `workshop facilitator learnings`
-
-Query the cross-cohort learnings log to review rotation signals from past and current workshops.
-Prefer invoking `harness --json workshop learnings` for machine-readable output.
-Supports flags: `--tag TAG`, `--instance ID`, `--cohort NAME`, `--limit N` (default 20).
-When the facilitator asks for rotation signals, captured observations, or what happened during past handoffs, use this command.
-If the learnings log is empty, say so and suggest capturing the first signal using the rotation capture panel in the facilitator dashboard.
-
 ### `workshop analyze`
 
 Review the team's repo against the handoff criteria in `workshop-skill/analyze-checklist.md`.
@@ -359,9 +221,7 @@ Relevant local files:
 - `workshop-skill/recap.md`
 - `workshop-skill/template-agents.md`
 - `workshop-skill/analyze-checklist.md`
-- `workshop-skill/closing-skill.md`
 - `workshop-skill/follow-up-package.md`
-- `workshop-skill/facilitator.md`
 - `materials/participant-resource-kit.md`
 - `materials/coaching-codex.md`
 - `docs/learner-resource-kit.md`

package/assets/workshop-bundle/bundle-manifest.json

@@ -1,8 +1,8 @@
 {
   "manifestVersion": 1,
   "bundleName": "harness-lab-workshop",
-  "bundleVersion": "0.3.2",
-  "contentHash": "579eac8240790ff7974b9cfdfba7f4c2ae0c901fbf3bf312e1017ad258069174",
+  "bundleVersion": "0.4.0",
+  "contentHash": "99a5b8475b6a4c11bc0652784d160a3a9d8fa3cfe38595c21bbe71d48159b3a4",
   "files": [
     {
       "path": "content/challenge-cards/.gitkeep",
@@ -10,11 +10,11 @@
     },
     {
       "path": "content/challenge-cards/deck.md",
-      "sha256": "d2523b1fbedd84faef5327affe5a698f44b8634c9eb0da8320dc8339bc5158fc"
+      "sha256": "00f4b0d08e3f77d3f73ad07c73561842dd479a1837a98cc9ba448e1a77db0d2e"
     },
     {
       "path": "content/challenge-cards/locales/en/deck.md",
-      "sha256": "f519c2dfa66801a90e1dbf8833e73bd03fbb001de9766286f9627750456a0b9b"
+      "sha256": "b6a4c7806cd64c96b23a213d44facb6c813004dc30047ddd441df854b59fc1c1"
     },
     {
       "path": "content/challenge-cards/print-spec.md",
@@ -32,6 +32,14 @@
       "path": "content/facilitation/codex-setup-verification.md",
       "sha256": "d137a5e729a1d443713a9e8431bffe169a1058d3e64c298688a6b7924fbdf3a8"
     },
+    {
+      "path": "content/facilitation/locales/en/codex-setup-verification.md",
+      "sha256": "22cccab9c416fd3be90ffc1b4cdacda2e9cb3dbc87996b6757fa8e892cb62b1c"
+    },
+    {
+      "path": "content/facilitation/locales/en/master-guide.md",
+      "sha256": "8457779270bc6dbcfa9ac35e1d4d6f2d0b9d6ca5f1711971cb0c575726e6c228"
+    },
     {
       "path": "content/facilitation/master-guide.md",
       "sha256": "c5f3df56380b3df498a92dc6de55e922b2c7722e53e4f6f2efbef9b76de1d163"
@@ -90,7 +98,15 @@
     },
     {
       "path": "content/talks/context-is-king.md",
-      "sha256": "2f666585220c50901fe91443904a127e3357aa71a92e93b10eafa17100eb105c"
+      "sha256": "58ec1705d61a8b742a93706765ec1307f62746ec5fc1315bd9d4c203b5a5bb65"
+    },
+    {
+      "path": "content/talks/locales/en/codex-demo-script.md",
+      "sha256": "9910eed4c759318b50bbb52683da4a0bf3274f376717ab15440c18317831852f"
+    },
+    {
+      "path": "content/talks/locales/en/context-is-king.md",
+      "sha256": "50f5b1bf964bdc941047f61dd59d657463aa3a23f8b5b50f1966883154ec796a"
     },
     {
       "path": "docs/harness-cli-foundation.md",
@@ -118,7 +134,7 @@
     },
     {
       "path": "materials/coaching-codex.md",
-      "sha256": "2390be079acde89b16380cdd0904fac2cbefcb9aa11c1fe256330b2dc2362ba9"
+      "sha256": "d6d03c8632ffae3dc52bc36f0d7fa6471204a52fe8a8b59dd47bd11bfa33fed4"
     },
     {
       "path": "materials/locales/en/participant-resource-kit.md",
@@ -126,15 +142,15 @@
     },
     {
       "path": "materials/participant-resource-kit.md",
-      "sha256": "c9c58ebf3e66a6f6823a06b5d938bc930eb3a768d3d23a2b4f18fe99b4b85a47"
+      "sha256": "5bd9df87c6964281945fbc9652122cc82bf3d11807baa35a5eb1269557895fbc"
     },
     {
       "path": "SKILL.md",
-      "sha256": "0188da9de8f517a09dc4d0e2eb14f395aa465048253bf0c719995e8a232a33e2"
+      "sha256": "806cb0abbe835e37ed3f76e2db053472dda272f87777e473d9c524d10fe1012c"
     },
     {
       "path": "workshop-blueprint/agenda.json",
-      "sha256": "91b4037578ce61d172e09941089b97180322552cb42bb52de87b3956e60b1ed0"
+      "sha256": "7cb25f1723945e1eb01e83ffb46eed0e3c988e3fdaed6767f513bedb9a94cf72"
     },
     {
       "path": "workshop-blueprint/control-surfaces.md",
@@ -142,19 +158,19 @@
     },
     {
       "path": "workshop-blueprint/day-structure.md",
-      "sha256": "22d6fec0422751439bd10049028ee12d140599707dbc6df248b4ff8517ee0c15"
+      "sha256": "5327b301f9d48efb2455d7377859bd25f87bcbaf56ce5542e9638320217ab933"
     },
     {
       "path": "workshop-blueprint/operator-guide.md",
-      "sha256": "c1cc4d64bfeed153e6b37d9e9fe8b270d052cd98fca17793891e04b37008149d"
+      "sha256": "eda21a849b8a7e9ce3ae69e0c038611773f4fdfdab518c990590a23941808f0c"
     },
     {
       "path": "workshop-blueprint/README.md",
-      "sha256": "e5cc8a87576988ce724b7ffacd86a4276aa6733bd4b9037d1f560a58da048308"
+      "sha256": "22dc35a0a1b8539b32b9c4f1ab2d6c095095a1e48078851e34d7f629e432b4fe"
     },
     {
       "path": "workshop-blueprint/teaching-spine.md",
-      "sha256": "3fd140be90cabb651907e71380c292a5b76746f97367adb23571a4fead1df6b4"
+      "sha256": "0fb9817f3622b9493db08c2e56aacdc149f76821981cc4b19e5831a385adc7bd"
     },
     {
       "path": "workshop-skill/.gitkeep",
@@ -162,7 +178,7 @@
     },
     {
       "path": "workshop-skill/analyze-checklist.md",
-      "sha256": "b1b5af58fc18f8400677a964eb3c1970015284d63101683fc8232bbea6cf8871"
+      "sha256": "7c774827062155b75f195fff7b184ac192d3ae8e0ea858562a7e3ee8da654c15"
     },
     {
       "path": "workshop-skill/closing-skill.md",
@@ -170,7 +186,7 @@
     },
     {
       "path": "workshop-skill/commands.md",
-      "sha256": "d0af2bcc53c9752be3b013da002c22d4a8c7a09dea1995075b82550947141736"
+      "sha256": "837c795baf133f220d3badf329c2484028f87209fb4e39cc729df54754b9a0a3"
     },
     {
       "path": "workshop-skill/facilitator.md",
@@ -178,7 +194,7 @@
     },
     {
       "path": "workshop-skill/follow-up-package.md",
-      "sha256": "3299b0cf49e90f87ec3090ed934234d8c06e502fd3305c4e69c8aadfe1b42e7e"
+      "sha256": "cea6ede3d6029938ceffca5ebf600796f24d6b0a5636132e21697bafe5df0b1f"
     },
     {
       "path": "workshop-skill/install.md",
@@ -186,11 +202,11 @@
     },
     {
       "path": "workshop-skill/locales/en/commands.md",
-      "sha256": "596af69cff67b770c284b4485c94bc39b511a60f3ff1b2b34f91f2c58a9f8b03"
+      "sha256": "17856fa19a44c3336709186cba171505db4b503d11bc16ad2fbc49f67d6c78a0"
     },
     {
       "path": "workshop-skill/locales/en/follow-up-package.md",
-      "sha256": "f941c29394f143b9e78d2d54ffb3e0643e421c310329ead784a13e788c8d8caf"
+      "sha256": "c5187d1852f647cedf648d7d07a2fe4ba7a211f2b5b2644f785a98c7c660628b"
     },
     {
       "path": "workshop-skill/locales/en/recap.md",
@@ -198,7 +214,7 @@
     },
     {
       "path": "workshop-skill/locales/en/reference.md",
-      "sha256": "2e941f974ae86c79131770d40302eec0e7968e217f36d8ff166065c7819c47b3"
+      "sha256": "ea6355498b8e49ed43eae51c17dbd18eff8243d186165c204e2e4d45765e7c69"
     },
     {
       "path": "workshop-skill/locales/en/setup.md",
@@ -210,12 +226,16 @@
     },
     {
       "path": "workshop-skill/reference.md",
-      "sha256": "438cfc517d5ff707ce737e81a7ec3f8098c08f8fd2589ac105aea968da39f9a6"
+      "sha256": "81f1f4bc31ac98a1ff30c049a5dcf7548c08b03d9f2e208dfaccd101813c1503"
     },
     {
       "path": "workshop-skill/setup.md",
       "sha256": "8a9a66372b49d504b5df45e0df3eac2835ef02ce79b7db1078fc85a928a36d5d"
     },
+    {
+      "path": "workshop-skill/SKILL-facilitator.md",
+      "sha256": "dab4428fd02059bee12269234931aac95b1863fe295c4bdd965eb50cc53d80b2"
+    },
     {
       "path": "workshop-skill/template-agents.md",
       "sha256": "a8647455ac66b79107d120258591e5e96cef394ed1b2acdb8a2ec4669469c5fe"

package/assets/workshop-bundle/content/challenge-cards/deck.md

@@ -1,40 +1,60 @@
 # Challenge Cards
 
-Karty nejsou body navíc. Jsou to malé zásahy, které zlepšují způsob práce s agentem i kvalitu handoffu.
+Karty nejsou body navíc. Jsou to malé zásahy, které zlepšují způsob práce s agentem i kvalitu handoffu.
+
+## Kde začít
+
+- Nemáte ještě `AGENTS.md`? Začněte první kartou z „Před obědem".
+- Máte `AGENTS.md`, ale žádné spustitelné ověření? Začněte druhou kartou.
+- Máte obojí? Vyberte si libovolnou kartu, která vás posune dál.
 
 ## Před obědem: postavte pracovní systém
 
-- `Vytvořte AGENTS.md jako mapu` — sepište cíl, build/test příkazy, trvalá pravidla a kam má další tým sáhnout jako první.
-- `Přidejte build/test příkazy` — agent musí umět ověřit výsledek bez ručního dovysvětlování.
-- `Napište skill pro code review` — formalizujte jednu review rutinu, kterou by uměl použít i cizí tým.
-- `Přesuňte pravidlo z hovoru do repa` — vše, co už tým řekl dvakrát nahlas, převeďte do `AGENTS.md`, README, runbooku nebo testu.
+- `AGENTS.md jako mapa` — Váš agent právě dostal úkol, ale nezná architekturu, pravidla ani co testovat. Vytvořte AGENTS.md se čtyřmi sekcemi: Goal / Context / Constraints / Done When. [Habit: Map before motion]
+
+- `Build/test příkazy` — Agent napsal kód, ale neumí ho ověřit bez vašeho ručního dovysvětlování. Přidejte build a test příkazy tak, aby agent i další tým uměl spustit kontrolu sám. [Habit: Verification is the trust boundary]
+
+- `Skill pro code review` — Tým opakuje v review vždy stejné připomínky. Formalizujte jednu review rutinu do skillu nebo checklistu, který by uměl použít i cizí tým. [Habit: Cleanup is part of build]
+
+- `Pravidlo z hovoru do repa` — Tým právě řekl nahlas nějaké pravidlo podruhé. Převeďte ho do AGENTS.md, README, runbooku nebo testu — co není v repu, neexistuje. [Habit: If it is not in the repo, it does not exist]
 
 ## Po rotaci: opravte signál, ne jen feature
 
-- `Použijte /plan před kódováním` — ukažte, z jakého plánu kroků tým vycházel, co z něj opravdu plní a jaký je další bezpečný krok.
-- `Rozdělte práci do více vláken` — zkuste dvě nezávislé linie práce a jednoho člověka na integraci.
-- `Delegujte úkol a vraťte se ke kontrole za 10 minut` — neskákejte agentovi do každého kroku, kontrolujte až výsledek.
-- `Přidejte nejmenší užitečné ověření` — zapište done criteria jako spustitelný check (unit test, tracer bullet nebo jednoduchý browser check) dřív, než agent dostane víc autonomie.
-- `Napište diagnózu po handoffu` — pojmenujte, co pomohlo, co chybělo a jaký je další bezpečný krok.
-- `Opravte jeden slabý signál v repu` — README, AGENTS.md, plán, runbook nebo check.
+- `Diagnóza po handoffu` — Právě jste zdědili repo, které jste nikdy neviděli. Napište, co vám pomohlo, co chybělo, co je rizikové a jaký je další bezpečný krok. [Habit: Map before motion]
+
+- `/plan před kódováním` — Tým se chce rovnou pustit do kódu, ale nikdo nevidí celkový plán. Použijte /plan, ukažte kroky, co plníte a jaký je další bezpečný krok. [Habit: Boundaries create speed]
+
+- `Rozdělte práci do více vláken` — Všichni v týmu pracují na jedné věci najednou. Zkuste dvě nezávislé linie práce a jednoho člověka na integraci. [Habit: Boundaries create speed]
+
+- `Delegujte a kontrolujte výsledek` — Skáčete agentovi do každého kroku. Dejte mu úkol s jasnými mantinely a vraťte se za 10 minut zkontrolovat výsledek, ne proces. [Habit: Verification is the trust boundary]
+
+- `Nejmenší užitečné ověření` — Agent říká, že je hotovo, ale nemáte jak to ověřit. Zapište done criteria jako spustitelný check (unit test, tracer bullet nebo browser check) dřív, než agent dostane víc autonomie. [Habit: Verification is the trust boundary]
+
+- `Opravte jeden slabý signál` — Přebírající tým musel hádat, co je hotové a co ne. Opravte jedno místo v README, AGENTS.md, plánu, runbooku nebo checku, které by to příště vyjasnilo. [Habit: Cleanup is part of build]
 
 ## Advanced
 
-- `Spusťte 2 paralelní Codex sessions` — rozdělte problém na dvě nezávislé části a porovnejte výstupy.
-- `Vytvořte runbook pro deployment` — i kdyby deploy zůstal jen simulovaný.
-- `Napište AGENTS.md pro podsložku` — ukažte, že kontext může být globální i lokální.
-- `Zaveďte garbage collection` — najděte jednu opakující se formu chaosu a proměňte ji v check, template nebo pravidlo.
+- `2 paralelní sessions` — Máte velký problém a jednu session. Rozdělte ho na dvě nezávislé části, paralelně je zpracujte a porovnejte výstupy. [Habit: Boundaries create speed]
+
+- `Runbook pro deployment` — Nikdo v týmu neví, jak by se výsledek nasadil. Vytvořte runbook pro deployment — i kdyby deploy zůstal jen simulovaný. [Habit: If it is not in the repo, it does not exist]
+
+- `AGENTS.md pro podsložku` — Hlavní AGENTS.md je příliš obecné pro konkrétní část projektu. Napište lokální AGENTS.md pro jednu podsložku, které přidá přesný kontext. [Habit: Map before motion]
+
+- `Garbage collection` — Stejný typ chaosu se v repu opakuje podruhé. Najděte ho a proměňte v check, template nebo pravidlo. [Habit: Cleanup is part of build]
 
 ## Meta
 
-- `Přesuňte trvalé pravidlo z promptu do AGENTS.md`.
-- `Přidejte sekci Done When ke každému tasku`.
-- `Napište README pro tým po rotaci, ne pro sebe`.
-- `Zapište, co je skutečně ověřené` — odlište hotové, rozpracované a jen předpokládané.
+- `Pravidlo z promptu do AGENTS.md` — Opakovaně píšete stejné omezení do promptu. Přesuňte ho do AGENTS.md, kde ho agent najde automaticky. [Habit: If it is not in the repo, it does not exist]
+
+- `Done When ke každému tasku` — Váš úkol nemá jasné done criteria. Přidejte sekci Done When, aby agent i review věděli, kdy je hotovo. [Habit: Verification is the trust boundary]
+
+- `README pro tým po rotaci` — Váš README popisuje, co jste udělali vy, ne co potřebuje vědět další tým. Přepište ho pro přebírající, ne pro sebe. [Habit: Map before motion]
+
+- `Co je skutečně ověřené` — Nevíte, co je hotové, co je rozpracované a co jen předpokládané. Zapište, co je skutečně ověřeno, a odlište to od zbytku. [Habit: Verification is the trust boundary]
 
-## Jak s kartami pracovat
+## Jak s kartami pracovat
 
-- Před obědem má každý tým splnit aspoň jednu kartu z části `Před obědem: postavte pracovní systém`.
-- Před rotací má být v repu dohledatelné, co bylo opravdu ověřeno a jaký je další bezpečný krok.
-- Po rotaci má každý tým splnit aspoň jednu kartu z `Po rotaci: opravte signál, ne jen feature`.
+- Před obědem má každý tým splnit aspoň jednu kartu z části „Před obědem: postavte pracovní systém".
+- Před rotací má být v repu dohledatelné, co bylo opravdu ověřeno a jaký je další bezpečný krok.
+- Po rotaci má každý tým splnit aspoň jednu kartu z „Po rotaci: opravte signál, ne jen feature".
 - Ostatní karty jsou dobrovolné. Berte je jako stretch cíle nebo inspiraci, když nevíte, co zlepšit dál.

package/assets/workshop-bundle/content/challenge-cards/locales/en/deck.md

@@ -2,39 +2,59 @@
 
 These cards are not bonus points. They are small interventions that improve both the way of working with the agent and the quality of the handoff.
 
+## Where to start
+
+- No `AGENTS.md` yet? Start with the first card from "Before lunch."
+- Have `AGENTS.md` but no executable verification? Start with the second card.
+- Have both? Pick any card that pushes you forward.
+
 ## Before lunch: build the working system
 
-- `Create AGENTS.md as a map` - write down the goal, build and test commands, durable rules, and where the next team should look first.
-- `Add build/test commands` - the agent must be able to verify the result without manual backfilling.
-- `Write a code review skill` - formalize one review routine that another team could use too.
-- `Move one rule from conversation into the repo` - anything the team has said out loud twice should be turned into `AGENTS.md`, README, a runbook, or a test.
+- `AGENTS.md as a map` — Your agent just received a task but knows nothing about the architecture, rules, or what to test. Create AGENTS.md with four sections: Goal / Context / Constraints / Done When. [Habit: Map before motion]
+
+- `Build/test commands` — The agent wrote code but cannot verify it without your manual explanation. Add build and test commands so the agent and the next team can run checks independently. [Habit: Verification is the trust boundary]
+
+- `Code review skill` — The team keeps giving the same review feedback. Formalize one review routine into a skill or checklist that another team could use too. [Habit: Cleanup is part of build]
+
+- `Rule from conversation into the repo` — The team just said a rule out loud for the second time. Move it into AGENTS.md, README, a runbook, or a test — if it is not in the repo, it does not exist. [Habit: If it is not in the repo, it does not exist]
 
 ## After rotation: fix the signal, not only the feature
 
-- `Use /plan before coding` - show which plan the team is working from, what is actually being executed, and what the next safe move is.
-- `Split the work into multiple threads` - try two independent work streams and one person on integration.
-- `Delegate a task and come back to check it in 10 minutes` - do not jump into every agent step; inspect the outcome instead.
-- `Add the smallest useful verification` - write the done criteria as an executable check (unit test, tracer bullet, or simple browser check) before the agent gets more autonomy.
-- `Write the post-handoff diagnosis` - name what helped, what was missing, and what the next safe move is.
-- `Fix one weak repo signal` - README, AGENTS.md, plan, runbook, or check.
+- `Post-handoff diagnosis` — You just inherited a repo you have never seen. Write down what helped, what was missing, what is risky, and what the next safe move is. [Habit: Map before motion]
+
+- `/plan before coding` — The team wants to jump straight into code but nobody sees the overall plan. Use /plan, show the steps, what you are executing, and what the next safe move is. [Habit: Boundaries create speed]
+
+- `Split work into multiple threads` — Everyone on the team is working on the same thing at once. Try two independent work streams and one person on integration. [Habit: Boundaries create speed]
+
+- `Delegate and check the result` — You are jumping into every agent step. Give it a task with clear constraints and come back in 10 minutes to check the result, not the process. [Habit: Verification is the trust boundary]
+
+- `Smallest useful verification` — The agent says it is done but you have no way to verify. Write done criteria as an executable check (unit test, tracer bullet, or browser check) before the agent gets more autonomy. [Habit: Verification is the trust boundary]
+
+- `Fix one weak signal` — The inheriting team had to guess what was done and what was not. Fix one spot in README, AGENTS.md, plan, runbook, or check that would clarify it next time. [Habit: Cleanup is part of build]
 
 ## Advanced
 
-- `Run 2 parallel Codex sessions` - split the problem into two independent parts and compare the outputs.
-- `Create a deployment runbook` - even if the deploy stays simulated.
-- `Write AGENTS.md for a subfolder` - show that context can be global and local at the same time.
-- `Introduce garbage collection` - find one repeating form of chaos and turn it into a check, template, or rule.
+- `2 parallel sessions` — You have a big problem and one session. Split it into two independent parts, process them in parallel, and compare the outputs. [Habit: Boundaries create speed]
+
+- `Deployment runbook` — Nobody on the team knows how the result would be deployed. Create a deployment runbook — even if the deploy stays simulated. [Habit: If it is not in the repo, it does not exist]
+
+- `AGENTS.md for a subfolder` — The main AGENTS.md is too generic for a specific part of the project. Write a local AGENTS.md for one subfolder that adds precise context. [Habit: Map before motion]
+
+- `Garbage collection` — The same type of chaos appears in the repo for the second time. Find it and turn it into a check, template, or rule. [Habit: Cleanup is part of build]
 
 ## Meta
 
-- `Move a durable rule from a prompt into AGENTS.md`.
-- `Add a Done When section to every task`.
-- `Write README for the team after rotation, not for yourself`.
-- `Record what is actually verified` - distinguish done, in progress, and assumed.
+- `Rule from prompt into AGENTS.md` — You keep writing the same constraint into prompts. Move it into AGENTS.md where the agent finds it automatically. [Habit: If it is not in the repo, it does not exist]
+
+- `Done When for every task` — Your task has no clear done criteria. Add a Done When section so the agent and reviewers know when it is finished. [Habit: Verification is the trust boundary]
+
+- `README for the team after rotation` — Your README describes what you did, not what the next team needs to know. Rewrite it for the inheriting team, not for yourself. [Habit: Map before motion]
+
+- `Record what is actually verified` — You cannot tell what is done, what is in progress, and what is just assumed. Record what is actually verified and distinguish it from the rest. [Habit: Verification is the trust boundary]
 
 ## How to use the cards
 
-- Before lunch, every team should complete at least one `Before lunch: build the working system` card.
+- Before lunch, every team should complete at least one card from "Before lunch: build the working system."
 - Before rotation, the repo should clearly show what was actually verified and what the next safe move is.
-- After rotation, every team should complete at least one `After rotation: fix the signal, not only the feature` card.
+- After rotation, every team should complete at least one card from "After rotation: fix the signal, not only the feature."
 - The other cards are optional. Treat them as stretch goals or prompts for what to improve next.

package/assets/workshop-bundle/content/facilitation/locales/en/codex-setup-verification.md

@@ -0,0 +1,7 @@
+---
+cs_reviewed: true
+---
+
+# Codex Setup Verification
+
+> English stub. Full translation pending. See the Czech source at `content/facilitation/codex-setup-verification.md`.

package/assets/workshop-bundle/content/facilitation/locales/en/master-guide.md

@@ -0,0 +1,7 @@
+---
+cs_reviewed: true
+---
+
+# Facilitation Master Guide
+
+> English stub. Full translation pending. See the Czech source at `content/facilitation/master-guide.md`.