@cairnkeep/cli 2.9.0 → 2.12.0

package/docs/harness-compatibility.md

@@ -12,14 +12,16 @@ commands, hooks, plugins, or trajectory adapters.
 | OpenCode | Memory MCP, commands, workflows, plugins, launcher | Exercised by Cairnkeep tests |
 | Kimi Code | Memory MCP, `AGENTS.md`, launcher, opt-in graph Skill | Launcher tested; remote MCP tested with Kimi Code 0.30.0; graph Skill contract-tested |
 | Qwen Code | Memory MCP, launcher | Launcher tested; stdio and remote MCP tested with Qwen Code 0.21.1 |
-| Pi | Native opt-in trajectory extension, launcher, and graph prompt | Exercised by Cairnkeep tests; no bundled MCP bridge |
-| Codex CLI | Memory MCP | Configuration supported; no Cairnkeep operating-layer assets or launcher |
+| Pi | Memory MCP through maintained local stdio extension, native opt-in trajectory extension, launcher, and graph prompt | Pi 0.84.1 validated minimum; deterministic and real bridge/lifecycle tests |
+| Codex CLI | Project-scoped memory MCP and launcher | Setup and launcher contract-tested on POSIX and simulated native Windows; project trust remains operator-controlled |
 | Other MCP clients | Memory plus optional domain-knowledge and context-pack tools | Protocol-compatible; not automatically runtime-tested |
 
 Only Claude Code and OpenCode currently receive the complete operating layer.
 Kimi receives one narrow graph Skill, while Pi receives one narrow graph prompt;
 neither is equivalent to the full commands, agents, hooks, and plugins surface.
 Qwen skills and hooks still require harness-specific adaptation and validation.
+Codex receives a project-local MCP entry and launcher, but not Cairnkeep-specific
+commands, hooks, agents, or automatic skill activation.
 
 Every MCP client receives complete tool annotations and may use a Cairnkeep
 least-authority profile independent of harness assets. Context-pack tools are
@@ -33,7 +35,35 @@ Pi, Qwen Code, Codex, and other shell-capable clients can invoke
 `graphify` executable are on `PATH`. `cairn sync-kimi --apply` registers a Kimi
 Skill as `/graphify` (or `/skill:graphify`), and `cairn sync-pi --apply`
 registers a Pi prompt template as `/graphify`; both delegate exclusively to
-that CLI. Neither adds an MCP bridge to Pi or expands the other support levels.
+that CLI. Pi sync separately installs the Cairnkeep-owned local stdio memory
+extension; it does not expand the other support levels.
+
+## Pi
+
+Run `cairn sync-pi --apply` explicitly to install
+`extensions/cairnkeep-memory.ts`, `extensions/cairnkeep-trajectory.ts`, and
+`prompts/graphify.md` under the Pi agent root. Use `--check` for drift and
+`cairn doctor` from a project that selected Pi for setup-aware diagnosis. Setup
+reports this machine command but never runs it automatically. Uninstall removes
+only those owned paths, backup-first.
+
+The memory extension supervises `cairn memory-server` as a local stdio child.
+It discovers the effective MCP catalog dynamically and preserves names,
+descriptions, input/output schemas, original content, `structuredContent`,
+`_meta`, failure behavior, and the exact tool annotations in trusted result
+`details`. Pi 0.84.1 exposes no native annotations field in its public tool API,
+so those annotations are not claimed as native model-facing metadata. Server
+feature gates, capability state, and least-authority profiles continue to
+decide which tools exist.
+
+Startup, calls, results, stderr retention, cancellation, and shutdown are
+bounded. The extension adds tools only: it does not run prompts, activate
+context-pack skills, create an autonomous loop, or add a remote transport.
+Pi 0.84.1 is the validated minimum. The v2.11 release matrix passed separate
+installations for that minimum and the explicitly versioned registry-current Pi
+release, together with Node.js 22/24/26, Bash 3.2, and native Windows. The
+executable paths were distinct; both reported 0.84.1 because that was also the
+registry-current release.
 
 ## Kimi Code
 
@@ -172,6 +202,37 @@ Git, and leave secret values as environment references.
 Qwen MCP configuration is documented at
 [Qwen Code MCP](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/).
 
+## Codex CLI
+
+Select Codex during setup to create a project-scoped local stdio entry and
+launcher:
+
+```bash
+cairn setup /path/to/project --git init --harness codex --memory local --yes
+cd /path/to/project
+./.ai/start-codex.sh
+```
+
+Native Windows uses `.\.ai\start-codex.cmd`. The generated
+`.codex/config.toml` contains only:
+
+```toml
+[mcp_servers.cairn-memory]
+command = "cairn"
+args = ["memory-server"]
+```
+
+Review this file before accepting Codex's project-trust prompt. Cairnkeep does
+not grant trust, edit the user-wide Codex configuration, or start Codex during
+setup. If an operator-owned `.codex/config.toml` already differs, setup reports
+`skipped` and leaves it unchanged; merge the table manually and run `cairn
+doctor` to verify the effective entry. Uninstall never removes an
+operator-owned configuration file.
+
+The launcher loads `.ai/.env`, runs optional pre/post hooks, changes to the
+project root, and passes all arguments to `codex`. It does not install native
+Codex Skills or instructions and does not activate approved context-pack skills.
+
 ## Candidate memory clients
 
 The following clients have documented MCP support and are reasonable adapter

package/docs/learning/CURRICULUM-MAP.md

@@ -1,7 +1,7 @@
 # Curriculum Coverage Map
 
-**Baseline:** Cairnkeep 2.9.0
-**Last reviewed:** 2026-08-06
+**Baseline:** Cairnkeep 2.12.0
+**Last reviewed:** 2026-08-13
 
 This map prevents the course from drifting behind the product. It assigns each
 user-facing surface to a lesson and records whether the lesson is complete or
@@ -14,7 +14,8 @@ been rehearsed.
 | Product surface | Introduced | Practised or operated | Learning status |
 |---|---|---|---|
 | Local stdio memory and MCP registration | L00-L02 | L03-L04 | L00-L03 Ready; L04 Brief |
-| Project bootstrap, launchers, and contributor mode | L02-L03 | L05 | L02-L03 Ready; L05 Brief |
+| Guided project setup, launchers, and bootstrap compatibility/contributor mode | L02-L03 | L05 and L23 | L02-L03 and L23 Ready; L05 Brief |
+| Declarative harness registry and Codex project-scoped MCP setup | L03 | L03 and L23 | Ready; project trust remains explicit |
 | Memory scopes, keys, search, supersession, and history | L04 | L04-L05 | Brief |
 | Wiki, alignment, and repository quality workflows | L05-L06 | L05-L06 | Brief |
 | Optional local code graph, graph inspection, and harness delegates | L18 | L18 | Brief; default off |
@@ -34,6 +35,9 @@ been rehearsed.
 | Reviewed, evaluated, reversible skill-file improvement | L19 | L19 | Ready; explicit and default off |
 | Complete MCP annotations and least-authority tool profiles | L20 | L20 | Ready; default profile remains full |
 | Immutable context packs and exact-digest skill approval | L21 | L21 | Ready; default off |
+| Native Windows x64 CLI, hooks, ACLs, scheduling, and recovery | L22 | L22 | Ready; PowerShell-native |
+| Guided project setup, selected harness state, and Git-less limitations | L03 | L03 and L23 | Ready |
+| Pi local stdio memory bridge, trusted annotation details, and explicit lifecycle | L23 | L23 | Ready; Pi 0.84.1 validated minimum |
 
 ## Release Review
 
@@ -55,7 +59,7 @@ repository remains the canonical source for explanations and scripts.
 | Checkpoint | Lessons | Purpose |
 |---|---|---|
 | `course-00-app` | L00-L02 | Plain synthetic application before Cairnkeep |
-| `course-01-bootstrap` | L03 | Neutral bootstrap and isolated environment |
+| `course-01-bootstrap` | L03 | Guided local setup, Codex project configuration, and isolated environment |
 | `course-02-memory` | L04-L05 | Memory lifecycle and derived knowledge |
 | `course-03-quality` | L06 | Repository review and deliberately vulnerable fixture |
 | `course-04-operation` | L07-L12 | Storage, routing, integrations, containers, overlays |
@@ -65,6 +69,8 @@ repository remains the canonical source for explanations and scripts.
 | `course-08-graph` | L18 | Optional local structural graph workflow |
 | `course-09-skill` | L19 | Validated skill improvement in a disposable project |
 | `course-10-trust-context` | L20-L21 | MCP authority profiles and offline context-pack lifecycle |
+| `course-11-windows` | L22 | Native PowerShell lifecycle, ACL inspection, and reversible uninstall |
+| `course-12-guided-setup` | L23 | Deterministic setup, Pi local stdio, recovery, and backup-first uninstall |
 
 ## Command Ownership
 
@@ -73,10 +79,11 @@ against `cairn help` so a new command cannot bypass a curriculum decision.
 
 | Command | Primary lesson |
 |---|---|
-| `cairn bootstrap` | L03 |
+| `cairn bootstrap` | L03 compatibility challenge |
+| `cairn setup` | L03 for Claude/Codex; advanced Pi lifecycle in L23 |
 | `cairn memory-server` | L02 |
 | `cairn sync` | L02 |
-| `cairn sync-pi` | L13 |
+| `cairn sync-pi` | L13 and L23 |
 | `cairn sync-kimi` | L02 |
 | `cairn doctor` | L03; advanced repair in L13-L14 |
 | `cairn trajectory` | L13 |

package/docs/learning/FEATURE-GUIDE.md

@@ -1,6 +1,6 @@
 # Cairnkeep feature guide
 
-**Baseline:** Cairnkeep 2.9.0
+**Baseline:** Cairnkeep 2.12.0
 
 This is the step-back map for choosing and operating Cairnkeep features. The
 [course labs](https://github.com/cairnkeep/cairnkeep-course-labs) provide one
@@ -8,13 +8,19 @@ synthetic Trail Ledger project with tagged states from a plain application to
 offline evaluation. Detailed contracts remain in the linked operating,
 storage, privacy, and lesson documents.
 
+Guided setup and the maintained Pi memory extension shipped in v2.11. The v2.12
+harness registry adds first-class Codex project setup without granting project
+trust. See [L03](lessons/L03-first-project.md) and
+[L23](lessons/L23-guided-setup.md) for the tested boundaries.
+
 ## The three-layer model
 
 1. **Memory server:** an MCP process that owns scoped durable storage. The
    default stdio setup runs on the current machine; installation never
    discovers or selects a remote host.
 2. **Project scaffold:** launchers, private environment, and `.planning/`
-   policy/derived-knowledge files created by `cairn bootstrap`.
+   policy/derived-knowledge files reconciled by `cairn setup`; `cairn bootstrap`
+   remains the deterministic compatibility primitive.
 3. **Operating layer:** harness commands, agents, and hooks installed by
    `cairn sync --apply` or the harness-specific equivalent.
 
@@ -48,6 +54,8 @@ prerequisites for ordinary memory.
 | Wiki and alignment | `/wiki-ingest`, `/wiki-query`, `/wiki-lint`, alignment files | Written only when invoked; reviewable `.planning/` artifacts | Re-run lint, inspect source citations, revert tracked changes normally | `course-02-memory` |
 | Local code graph | `cairn graph build|query|status|diff|explain|path`; `/graphify` delegates | Default off; optional isolated `graphify` executable; incremental work under `graphify-out/`, published view under `.planning/graphs/` | Ignore both derived locations; check status and source before trusting a result; use `--force` only after intentional deletion; uninstall adapters separately | `course-08-graph` |
 | Repository quality | `/repo-review`, `/security-audit` | On-demand workflow; findings are hypotheses until reproduced | Require file/line evidence and regression tests | `course-03-quality` |
+| Guided project setup | `cairn setup PATH --git init\|existing\|none --harness LIST --memory local\|none --yes` | Reconciles only selected project assets from one harness registry; private `.ai/cairnkeep.json`; machine sync is never automatic | Repeat deterministically, run doctor, or replay its recovery command; Git-less mode remains limited | `course-12-guided-setup` |
+| Codex project memory | Select `--harness codex --memory local` | Writes `.codex/config.toml` plus POSIX/native Windows launchers; local stdio; user-wide configuration and trust remain untouched | Review the MCP table, accept Codex project trust, run doctor, and relaunch; uninstall is backup-first | `course-01-bootstrap` |
 
 ## Storage and optional topology
 
@@ -62,6 +70,7 @@ prerequisites for ordinary memory.
 | Managed overlays | Separate distribution manifest, wrapper, profile lock, fleet and rollback gates | Policy and secrets belong in the private distribution/machine config, never core | `overlay info`, doctor, fleet dry run/current state, rollback | `course-04-operation` |
 | MCP tool profiles | `cairn mcp-tools set full|read-only|custom` | Strict mode-`0600` project config; process overrides take precedence; profile only removes tools | Inspect catalog/status digest; reset and restart MCP | `course-10-trust-context` |
 | Context packs | Manual local or commit-pinned Git install plus project enablement | Immutable objects and atomic pointers under `CAIRN_PACK_BASE_DIR`; no background sync | Validate, inspect digest, check/apply update, disable/remove | `course-10-trust-context` |
+| Pi local stdio memory | Select Pi during setup, then explicitly run `cairn sync-pi --apply` | Local memory-server child; dynamic effective tool catalog; annotations retained in trusted details, not a native Pi field | `cairn sync-pi --check`, `cairn doctor`, cancel one call, then observe awaited shutdown with no orphan | `course-12-guided-setup` |
 
 ## Evidence, governance, and measurement
 
@@ -82,8 +91,10 @@ prerequisites for ordinary memory.
 ## Harness and maintenance checks
 
 - Use a generated launcher so project environment and hooks are repeatable.
+- For Codex, review `.codex/config.toml` and accept project trust; no machine
+  sync is required for the memory-only integration.
 - Run `cairn sync --check` after every core upgrade; apply only reported drift.
-- Run `cairn sync-pi --check` when the optional Pi capture/graph adapter is installed.
+- Run `cairn sync-pi --check` when the Pi memory/trajectory/graph assets are installed.
 - Run `cairn sync-kimi --check` when the optional Kimi graph Skill is installed.
 - Use `cairn doctor --repair` only after preserving the affected store and only
   for repairable derived indexes/metadata.

package/docs/learning/README.md

@@ -8,7 +8,8 @@ publication material.
 
 Choose the shortest track that matches your goal:
 
-- [Quickstart](tracks/quickstart.md) - prove the core value in about 75 minutes.
+- [Quickstart](tracks/quickstart.md) - prove the core value, including the
+  one-command Codex project path and the explicit Pi lifecycle, in about 110 minutes.
 - [Practitioner](tracks/practitioner.md) - adopt Cairnkeep in daily project work.
 - [Evidence and evaluation](tracks/evidence-and-evaluation.md) - inspect optional
   session evidence, govern capabilities, and measure changes without overstating
@@ -33,7 +34,7 @@ expanded only after their labs are executable.
 | L00 | [Why Cairnkeep?](lessons/L00-why-cairnkeep.md) | Ready | 10 min |
 | L01 | [Try it safely](lessons/L01-safe-trial.md) | Ready | 15 min |
 | L02 | [Install the local workflow](lessons/L02-installation.md) | Ready | 25 min |
-| L03 | [Bootstrap the first project](lessons/L03-first-project.md) | Ready | 25 min |
+| L03 | [Set up the first project](lessons/L03-first-project.md) | Ready | 25 min |
 | L04 | [Memory fundamentals](lessons/L04-memory-fundamentals.md) | Brief | 35 min |
 | L05 | [The daily workflow](lessons/L05-daily-workflow.md) | Brief | 40 min |
 | L06 | [Repository review and security](lessons/L06-repository-quality.md) | Brief | 45 min |
@@ -52,6 +53,8 @@ expanded only after their labs are executable.
 | L19 | [Validated skill improvement](lessons/L19-validated-skill-improvement.md) | Ready | 50 min |
 | L20 | [Least-authority MCP tool profiles](lessons/L20-mcp-tool-profiles.md) | Ready | 25 min |
 | L21 | [Immutable context packs and skill approval](lessons/L21-context-packs.md) | Ready | 40 min |
+| L22 | [Operate Cairnkeep on native Windows](lessons/L22-native-windows.md) | Ready | 30 min |
+| L23 | [Guided setup and Pi memory](lessons/L23-guided-setup.md) | Ready | 35 min |
 
 The [curriculum coverage map](CURRICULUM-MAP.md) records where every public
 feature is introduced, practised, and operated. It also marks design-only work

package/docs/learning/lessons/L00-why-cairnkeep.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 10 minutes
-**Tested with:** Cairnkeep 2.9.0
+**Tested with:** Cairnkeep 2.12.0
 
 ## Outcome
 

package/docs/learning/lessons/L01-safe-trial.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 15 minutes
-**Tested with:** Cairnkeep 2.9.0
+**Tested with:** Cairnkeep 2.12.0
 
 ## Outcome
 
@@ -26,7 +26,7 @@ ephemeral; the named course volume is persistent.
 1. Pull the public image:
 
    ```bash
-   podman pull ghcr.io/cairnkeep/cairnkeep:2.9.0
+   podman pull ghcr.io/cairnkeep/cairnkeep:2.12.0
    ```
 
 2. Start the stdio server with a read-only root filesystem and no Linux
@@ -38,7 +38,7 @@ ephemeral; the named course volume is persistent.
      --read-only --cap-drop=all --security-opt=no-new-privileges \
      --tmpfs=/tmp:rw,noexec,nosuid,size=64m,mode=1777 \
      --volume cairnkeep-course-data:/data:Z,U \
-     ghcr.io/cairnkeep/cairnkeep:2.9.0 stdio
+     ghcr.io/cairnkeep/cairnkeep:2.12.0 stdio
    ```
 
 3. The process waits quietly for MCP input. Press `Ctrl-C` after confirming it

package/docs/learning/lessons/L02-installation.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 25 minutes
-**Tested with:** Cairnkeep 2.9.0 and Node.js 22 or newer
+**Tested with:** Cairnkeep 2.12.0 and Node.js 22 or newer
 
 ## Outcome
 
@@ -13,7 +13,8 @@ layer, and distinguish a complete installation from a partial one.
 ## Prerequisites
 
 - Node.js 22 or newer and npm.
-- Claude Code installed for the commands below. OpenCode, Kimi Code, and Qwen Code users
+- Claude Code installed for the full operating-layer commands below. Codex CLI
+  users can take the project-scoped path in L03. OpenCode, Kimi Code, and Qwen Code users
   should follow the equivalent setup in
   [the operating guide](../../operating.md).
 - Permission to install an npm package globally for your user.
@@ -26,8 +27,13 @@ A complete setup has three independent parts:
 2. the MCP registration used by the harness;
 3. the operating layer containing commands, agents, hooks, and templates.
 
-`cairn bootstrap` configures a project later; it does not perform the first two
-machine-level steps.
+`cairn setup` configures a project later; it does not perform the first two
+machine-level steps. `cairn bootstrap` remains the compatibility primitive for
+scripts and overlays that already own their setup policy.
+
+Codex is the simpler memory-only exception: L03 writes its project-scoped MCP
+entry and launcher, so it needs no user-wide MCP registration or machine-level
+sync. Codex project trust remains an explicit operator decision.
 
 ## Exercise
 
@@ -41,7 +47,7 @@ machine-level steps.
 2. Install Cairnkeep:
 
    ```bash
-   npm install --global @cairnkeep/cli@2.9.0
+   npm install --global @cairnkeep/cli@2.12.0
    cairn --version
    ```
 
@@ -72,6 +78,15 @@ machine-level steps.
    Use `cairn completion zsh` or `cairn completion fish` for those shells.
    Completion is a convenience and is not another runtime component.
 
+   On native Windows PowerShell, use:
+
+   ```powershell
+   Invoke-Expression (& cairn completion powershell | Out-String)
+   ```
+
+   Project setup emits `.cmd` launchers on Windows; use
+   `.\.ai\start-claude.cmd` instead of the Unix `.sh` launcher.
+
 ## Verify
 
 Run both checks:
@@ -99,8 +114,9 @@ installation.
 This registration starts `cairn memory-server` locally as a stdio child. It
 does not discover a server, send memory to a remote host, configure embeddings,
 enable session capture, or enable an optional document-RAG integration. Pi uses
-the separate `cairn sync-pi` trajectory and graph-prompt adapter and still needs
-a user-selected bridge if Pi should expose MCP memory tools.
+the separate, explicit `cairn sync-pi --apply` command to install Cairnkeep's
+maintained local stdio memory extension, trajectory extension, and graph prompt.
+Project setup records the Pi selection but never changes machine-level Pi assets.
 
 Kimi Code can use the same memory server through its generated
 `.ai/start-kimi.sh` launcher, but its HTTP MCP configuration requires a literal
@@ -136,4 +152,4 @@ Do not delete memory stores as part of a course cleanup.
 - `sync --check` is the non-writing drift check.
 - Default stdio memory is local.
 
-Next: [L03 - Bootstrap the first project](L03-first-project.md).
+Next: [L03 - Set up the first project](L03-first-project.md).

package/docs/learning/lessons/L03-first-project.md

@@ -1,14 +1,15 @@
-# L03 - Bootstrap the first project
+# L03 - Set up the first project
 
 **Status:** Ready
 **Track:** Quickstart
 **Time:** 25 minutes
-**Tested with:** Cairnkeep 2.9.0
+**Tested with:** Cairnkeep 2.12.0
 
 ## Outcome
 
-You can bootstrap a disposable project, verify its wiring, store one accepted
-fact, and recall it from a new harness session.
+You can use the guided setup contract on an empty directory, choose Claude Code
+or Codex CLI, verify its Git and harness wiring, store one accepted fact, and
+recall it from a new session.
 
 ## Prerequisites
 
@@ -18,22 +19,32 @@ fact, and recall it from a new harness session.
 
 ## Exercise
 
-1. Create a disposable repository:
+1. Create an empty disposable project directory:
 
    ```bash
    mkdir -p "$HOME/cairnkeep-course/first-project"
    cd "$HOME/cairnkeep-course/first-project"
-   git init
-   printf '# Cairnkeep course project\n' > README.md
    ```
 
-2. Bootstrap the project:
+2. Choose one harness and run the deterministic form of guided setup. The
+   explicit flags make the
+   exercise reproducible while exercising the same preflight as interactive
+   `cairn setup`:
 
    ```bash
-   cairn bootstrap "$PWD"
+   # Full operating-layer route from L02:
+   cairn setup "$PWD" --git init --harness claude --memory local --yes
+
+   # Or the self-contained Codex memory route:
+   # cairn setup "$PWD" --git init --harness codex --memory local --yes
    cp .ai/env.example .ai/.env
    ```
 
+   Setup must create the Git repository, generate only the selected harness
+   assets, and write the private `.ai/cairnkeep.json` setup record. Codex also
+   receives `.codex/config.toml`; review it and accept Codex's project-trust
+   prompt before launching.
+
 3. Keep optional endpoint and model values unset for this local exercise. Run
    diagnostics:
 
@@ -45,10 +56,11 @@ fact, and recall it from a new harness session.
    and evaluation flags unset. The quickstart proves core memory without
    silently changing the amount of retained data.
 
-4. Launch Claude Code through the generated project launcher:
+4. Launch the selected harness through its generated project launcher:
 
    ```bash
    ./.ai/start-claude.sh
+   # Codex route: ./.ai/start-codex.sh
    ```
 
 5. In the harness, store a deliberately synthetic convention:
@@ -79,9 +91,11 @@ The lesson is complete only if:
 
 | Symptom | Cause | Recovery |
 |---|---|---|
-| Launcher is missing | A different directory was bootstrapped | Run `pwd`, then bootstrap that exact path |
+| Setup refuses the target | The directory is non-empty or its Git state conflicts with `--git init` | Preserve the directory, inspect it, then select `--git existing` or use a genuinely empty disposable path |
+| Launcher is missing | A different directory was configured or Claude was not selected | Run `pwd`, inspect `.ai/cairnkeep.json`, then replay the recovery command from `cairn doctor` |
 | `.ai/.env` is missing | Only the example is generated | Copy `.ai/env.example` to `.ai/.env` |
-| `cairn-memory` is unavailable | L02 MCP registration is absent or stale | Run `claude mcp get cairn-memory`, repair it, then restart Claude Code |
+| `cairn-memory` is unavailable in Claude | L02 MCP registration is absent or stale | Run `claude mcp get cairn-memory`, repair it, then restart Claude Code |
+| `cairn-memory` is unavailable in Codex | Project configuration was skipped or the project is not trusted | Review/merge `.codex/config.toml`, rerun setup, then accept project trust and relaunch |
 | Slash commands are unknown | Operating assets were not loaded | Run `cairn sync --check`, apply if needed, then restart the harness |
 | Recall works only in the first session | Sessions used different storage routing | Compare launchers and environment, then inspect `cairn memory path` |
 
@@ -105,13 +119,18 @@ synthetic memory through the normal memory review/delete workflow if required.
 
 ## Optional challenge
 
-Repeat bootstrap with `--untracked` in another disposable Git repository, then
-inspect `.git/info/exclude` to see how contributor mode avoids shared changes.
+Create another disposable Git repository and run `cairn bootstrap --untracked`
+there. Inspect `.git/info/exclude` to see how the compatibility primitive keeps
+contributor-mode scaffolding out of shared changes.
 
 ## Recap
 
-- Bootstrap is project-specific and follows machine setup.
+- Guided setup owns target preflight, Git choice, harness selection, and a
+  private reconciliation record.
+- Bootstrap remains available for compatibility and contributor workflows.
 - The generated launcher establishes a repeatable project environment.
+- Codex memory setup is project-scoped and does not silently grant trust or
+  modify the user-wide Codex configuration.
 - Persistence is proven only after a new session recalls the accepted fact.
 
 Next: [L04 - Memory fundamentals](L04-memory-fundamentals.md).

package/docs/learning/lessons/L19-validated-skill-improvement.md

@@ -3,7 +3,7 @@
 **Status:** Ready
 **Track:** Evidence and Evaluation
 **Time:** 50 minutes
-**Tested with:** Cairnkeep 2.9.0
+**Tested with:** Cairnkeep 2.12.0
 
 ## Outcome
 

package/docs/learning/lessons/L20-mcp-tool-profiles.md

@@ -1,7 +1,7 @@
 # L20 - Least-authority MCP tool profiles
 
 **Status:** Ready
-**Tested with:** Cairnkeep 2.9.0 and Node.js 22 or newer
+**Tested with:** Cairnkeep 2.12.0 and Node.js 22 or newer
 **Time:** 25 minutes
 
 ## Outcome

package/docs/learning/lessons/L21-context-packs.md

@@ -1,7 +1,7 @@
 # L21 - Immutable context packs and skill approval
 
 **Status:** Ready
-**Tested with:** Cairnkeep 2.9.0 and Node.js 22 or newer
+**Tested with:** Cairnkeep 2.12.0 and Node.js 22 or newer
 **Time:** 40 minutes
 
 ## Outcome

package/docs/learning/lessons/L22-native-windows.md

@@ -0,0 +1,83 @@
+# L22 - Operate Cairnkeep on native Windows
+
+**Status:** Ready
+**Track:** Operator
+**Time:** 30 minutes
+**Tested with:** Cairnkeep 2.12.0, Windows x64, and Node.js 22 or newer
+
+## Outcome
+
+You can prove that Cairnkeep is running natively from PowerShell, run guided
+setup on an empty path containing spaces, inspect its security boundary, and
+perform a reversible uninstall without relying on WSL or Git Bash.
+
+## Exercise
+
+From PowerShell:
+
+```powershell
+npm install --global @cairnkeep/cli@2.12.0
+cairn version
+
+$Lab = Join-Path $env:TEMP 'Cairnkeep Windows Lab'
+New-Item -ItemType Directory -Force -Path $Lab | Out-Null
+cairn setup $Lab --git init --harness claude --memory local --yes
+cairn sync --apply --live-root (Join-Path $Lab '.claude-test')
+cairn sync --check --live-root (Join-Path $Lab '.claude-test')
+Push-Location $Lab
+cairn doctor
+Pop-Location
+```
+
+Verify that `.git`, `.ai/cairnkeep.json`, `.ai/start-claude.cmd`,
+`.ai/start-harness.ps1`, and the managed Claude assets exist. `cairn doctor`
+must identify native Windows x64 and complete an MCP stdio handshake.
+
+## Permission check
+
+```powershell
+Get-Acl (Join-Path $Lab '.ai\capabilities.json') | Format-List
+```
+
+Managed private files remove inherited broad access and retain only the current
+identity, Local System, and Administrators. Do not replace this with a Unix-mode
+check; Windows authorization is an ACL contract.
+
+## Recovery exercise
+
+```powershell
+cairn uninstall --dry-run --live-root (Join-Path $Lab '.claude-test') $Lab
+cairn uninstall --yes --live-root (Join-Path $Lab '.claude-test') $Lab
+```
+
+The command prints the timestamped backup location. Inspect `manifest.json` and
+`revert.ps1`; run the revert script only if you intentionally want to restore
+the removed managed assets.
+
+## Common failures
+
+| Symptom | Cause | Recovery |
+|---|---|---|
+| `cairn.cmd` is not found | npm's global directory is not on `PATH` | Run `npm prefix -g`, add the resulting directory to the user `PATH`, then open a new PowerShell session |
+| Hook registration reports drift | Managed `.cmd` hook or settings entry is absent | Run `cairn sync --apply`, then repeat `cairn sync --check` |
+| Memory export fails | `sqlite3.exe` is absent | Install SQLite and confirm `Get-Command sqlite3.exe`; runtime and import remain available |
+| A private-state check fails | The file inherited a broader ACL | Preserve the file, inspect it with `Get-Acl`, and recreate it through the owning Cairnkeep command |
+
+## Privacy and trust boundary
+
+Native support changes process, path, and permission mechanics; it does not
+enable a network, model, capture, artifact, context-pack, or capability flag.
+The Windows ACL is a local-host access boundary, while pack digests establish
+content integrity rather than publisher authenticity. Task Scheduler and purge
+operations remain separate explicit actions.
+
+## Boundaries
+
+- Windows x64 is native; Windows ARM64 is currently x64 emulation.
+- `sqlite3.exe` is optional for runtime and import, but required for a WAL-safe
+  memory export.
+- WSL is a separate Linux topology. Git Bash is not native-Windows evidence.
+- Task Scheduler changes remain opt-in through `cairn audit-timer`.
+
+See [Native Windows operation](../../native-windows.md) for the complete
+platform contract.