loadout-ai 0.6.0 → 0.8.0

package/CHANGELOG.md

@@ -2,6 +2,78 @@
 
 ## Unreleased
 
+## 0.8.0 - 2026-09-02
+
+### Security
+
+- Reject a remote registry bundle whose `digest` is not a SHA-256 hex string,
+  and verify the resolved cache path stays under the cache root, before any
+  recursive delete. A crafted digest could previously escape the cache and
+  delete an arbitrary user-accessible directory.
+- Fail closed in the safety scanner. Files that are oversized, unreadable, or
+  too deeply nested are reported as a blocking `uninspectable` finding instead
+  of being skipped silently, so an unreviewable file can no longer produce a
+  clean report.
+- Apply a timeout, byte cap, and file cap to every repository fetch by default
+  rather than only when a caller opts in, and bound registry responses by time
+  and decoded size.
+
+### Fixed
+
+- Parse the handoff log line by line. A single truncated write previously made
+  the whole inbox appear empty; good lines now survive and the corrupt line is
+  reported.
+- Settle handoff tasks on `error` and `cancel` as well as `done`, via an
+  explicit `resolves` field, so a failed task no longer stays pending forever.
+- Migrate handoff instruction blocks already written into `CLAUDE.md` and
+  `AGENTS.md` that still name retired commands.
+- Report installed skills as a count of skills rather than a sum of every
+  nested file, which overstated 44 skills as 584 items.
+
+### Changed
+
+- Generate shell completions from the Commander command tree so they cannot
+  advertise commands the CLI does not register.
+- Rebuild `loadout route` around a routing policy the user owns
+  (`~/.loadout/routing.json`, three buckets) instead of a fixed phase-to-tier
+  table, and narrow the model catalog to the current Claude and GPT-5.6 tiers.
+- Collapse handoff to a single command that sets itself up on first use.
+
+### Added
+
+- `scripts/check-documented-commands.mjs` in the evidence gate: documentation
+  may no longer reference a command the CLI does not have.
+
+## 0.7.0 - 2026-08-31
+
+### Added
+
+- First-party skills (`loadout skills list|install|remove`) shipping
+  `loadout-router` and `loadout-curator`, so Loadout is usable from inside an
+  agent conversation rather than only from a terminal.
+
+### Changed
+
+- Retire 15 redundant or dead-end commands, taking the surface from 66 to 26.
+- Group the 86 flat modules in `src/core` into eight domains.
+- Drop "Boost" from the mode names and explain that Maximum stays disabled.
+
+## 0.6.0 - 2026-08-31
+
+### Added
+
+- `loadout route`, recommending a model tier for a task with real pricing.
+- `loadout handoff`, a shared task log between Claude Code and Codex.
+
+### Changed
+
+- Rewrite `loadout doctor` output around a health grade and actionable next
+  steps rather than a per-component dump.
+
+### Fixed
+
+- Resolve `LOADOUT_VERSION` from both source and built layouts.
+
 ## 0.5.9 - 2026-07-21
 
 ### Fixed

package/README.md

@@ -8,7 +8,8 @@
 
 <p align="center">
   <strong>The package manager for your AI coding setup.</strong><br>
-  Discover broadly. Activate the right tools for each project. Stay current without starting over.
+  Install skills across 12 agents. Route each task to the right model.<br>
+  Hand work between Claude Code and Codex. Undo any of it.
 </p>
 
 <p align="center">
@@ -21,14 +22,45 @@
 </p>
 
 <p align="center">
+  <a href="#what-it-looks-like">See it</a> ·
   <a href="#install">Install</a> ·
-  <a href="#why-loadout">Why Loadout</a> ·
-  <a href="#profiles">Profiles</a> ·
-  <a href="#catalog-and-discovery">Discover</a> ·
+  <a href="#use-it-from-inside-your-agent">Use it in your agent</a> ·
+  <a href="#working-across-two-agents">Two agents</a> ·
+  <a href="#why-loadout">Why</a> ·
   <a href="#trust-and-limits">Trust</a> ·
   <a href="#command-reference">Commands</a>
 </p>
 
+## What it looks like
+
+```console
+$ loadout status
+Loadout — grade A: Healthy and up to date
+
+✓ Claude Code
+  ~/.claude/skills
+  43 skills | supports: skill, command, agent, mcp, plugin, root
+✓ Codex
+  ~/.agents/skills
+  30 skills | supports: skill, command, agent, mcp, plugin, root
+
+$ loadout route
+Default routing policy (not saved yet)
+
+  hard    Claude Opus 5    $5/$25 per M
+          architecture, security, migrations, tricky debugging, risky review
+  normal  Claude Sonnet 5  $3/$15 per M
+          most implementation, ordinary debugging, refactors
+  cheap   GPT-5.6 Luna     $0.2/$1.2 per M
+          tests, docs, boilerplate, renames, mechanical edits
+
+Change it:  loadout route --set normal=gpt-5.6-terra
+```
+
+The routing policy is a file you own, not a table I decided for you. Loadout
+knows which agents you actually have, prices the tradeoff before you spend the
+tokens, and previews and snapshots every write.
+
 ## Install
 
 You need Node.js 20 or newer and Git.
@@ -42,6 +74,50 @@ The second command detects your agents and previews the 30-skill Stable loadout.
 Nothing changes until you approve it. If anything goes wrong, start with the
 [user test guide](./docs/USER_TEST_GUIDE.md).
 
+For a reproducible install, pin the release: `npm install --global loadout-ai@0.8.0`.
+
+## Use it from inside your agent
+
+A CLI you have to leave your agent to run is a context switch. Loadout ships its
+own skill so you do not have to:
+
+```bash
+loadout skills install loadout-router --yes
+```
+
+Start a new agent session and just ask, in the conversation you are already in:
+
+> _"Which model should I use to refactor this auth module?"_
+> _"I'm running low on usage — what should I switch to?"_
+> _"Hand the test writing to Codex."_
+
+The skill teaches your agent to call `loadout route` and `loadout handoff` and act
+on the results. It wraps the CLI rather than embedding a copy of the model table,
+so pricing and model coverage update when Loadout updates instead of going stale
+in a markdown file.
+
+`loadout skills list` shows what ships with Loadout and what is already installed.
+
+## Working across two agents
+
+If you pay for both Claude and a ChatGPT plan, the two agents cannot see each
+other. Loadout gives them a shared, append-only task log:
+
+```bash
+loadout handoff codex "write unit tests for auth" --context "see src/auth.ts"
+```
+
+That is the whole thing. The first send creates the log and adds a short managed
+block to `CLAUDE.md` and `AGENTS.md` telling each agent to check its inbox at the
+start of a session. Only the text between the `loadout:handoff` markers is
+managed; the rest of your file is left alone.
+
+```bash
+loadout handoff codex      # what is waiting for codex
+loadout handoff            # everything pending, both directions
+loadout handoff --done 4f2a1c
+```
+
 ## How it works
 
 **Choose -> Inspect -> Preview -> Apply -> Undo**
@@ -59,7 +135,7 @@ This is an explicitly abridged transcript from a disposable Stable run. A litera
 ```console
 $ loadout setup --mode stable
 …
-Loadout: Stable Boost
+Loadout: Stable
 Detected agents: Claude Code, Cursor, Codex
 Catalog selection: 4 repositories
 Ready to install: 4 skill repositories (30 agent skill directories)
@@ -73,12 +149,10 @@ $ loadout rollback
 Restored snapshot <snapshot-id>
 
 $ loadout route design the authentication system
-Phase:    plan
-Tier:     Frontier (deep reasoning)
-Models:   Claude Opus 5 ($5/$25)
-          GPT-5.6 Sol ($5/$30)
-Agents:   claude-code
-Why:      Architecture and decomposition need deep reasoning to avoid costly rework
+Task:   design the authentication system
+
+Bucket: hard — architecture, security, migrations, tricky debugging, risky review
+Use:    Claude Opus 5  ($5/$25 per M)
 
 $ loadout doctor
 loadout doctor — HEALTHY
@@ -106,6 +180,12 @@ coding agents without making you rebuild the setup for every agent and every pro
 Most extension tools begin with a repo you already know. Loadout begins one step
 earlier: **what is actually worth knowing?** It stays with you after installation.
 
+Everything on this page is enforced. `docs/evidence/readme-claims.json` records
+each material claim with the code or command that proves it, and CI fails the
+build when the README and the implementation disagree — including the pinned
+version in the install line above. A README that cannot drift is a strange thing
+to build, and it is the reason the rest of this page is worth believing.
+
 Loadout watches a much wider catalog than it activates. You can keep thousands of
 technically screened skill copies in the disabled Maximum library, discover new projects as
 they appear, and let each codebase pull a focused active set instead of dumping
@@ -142,7 +222,7 @@ you can run yourself.
 
 ## Stable workflow
 
-### Stable Boost: install the essentials and start building
+### Stable: install the essentials and start building
 
 Stable is the recommended daily driver: **30 selected skill directories from four
 pinned public sources**, installed into each agent you choose. It covers planning,
@@ -199,9 +279,31 @@ checked by `loadout update` without moving them to a different agent path.
 
 ## Profiles
 
-Loadout is opinionated when you want it to be and precise when you do not.
+Loadout is opinionated when you want it to be and precise when you do not. The
+modes differ in one thing: how much of the reviewed catalog they install.
+
+| Mode      | Sources               | Skills | Active by default                |
+| --------- | --------------------- | ------ | -------------------------------- |
+| `stable`  | 4                     | 30     | yes — recommended starting point |
+| `power`   | 8                     | 56     | yes                              |
+| `maximum` | all reviewed          | all    | **no — downloaded but disabled** |
+| `custom`  | your `--package` list | varies | yes                              |
+
+**Maximum is the one worth understanding.** It downloads the entire reviewed
+library and leaves every skill _disabled_. Nothing reaches an agent prompt until
+a project activates what it needs:
+
+```bash
+loadout setup --mode maximum --yes
+cd ~/code/my-app
+loadout optimize --project .   # scans the repo, proposes an active set
+loadout activate               # enable just those here
+```
+
+That trade is deliberate: disk is cheap and context is not. A large disabled
+library plus a small active set beats installing everything into every prompt.
 
-### Power Boost: a larger cross-project toolkit
+### Power: a larger cross-project toolkit
 
 Power draws a skill-level allowlist from eight major collections. The prepared set
 is deduplicated and invalid units are quarantined, so the final count can be lower
@@ -349,7 +451,7 @@ Loadout does not claim there is one universally “best” configuration. Recomm
 
 <!-- loadout:daily-discovery:start -->
 
-**Discovery snapshot (generated 2026-08-30):** [237 repositories observed](./docs/DISCOVERED.md), including 218 uncataloged review candidates and 19 repositories already in the inspected catalog.
+**Discovery snapshot (generated 2026-09-02):** [239 repositories observed](./docs/DISCOVERED.md), including 221 uncataloged review candidates and 18 repositories already in the inspected catalog.
 <!-- loadout:daily-discovery:end -->
 
 The checked-in discovery report proves only its dated snapshot, not the success of every scheduled run. Use `loadout discover --source all --queue`, `loadout review-queue`, and `loadout candidate inspect owner/repository` to inspect candidates before catalog promotion.
@@ -392,7 +494,7 @@ Configured CI platforms describe a manually triggered workflow, not evidence tha
 
 <!-- loadout:support-summary:end -->
 
-Configured paths and disposable filesystem lifecycle tests do not prove that native applications recognize or execute installed skills. Use `loadout capabilities --inspect` for the local component matrix.
+Configured paths and disposable filesystem lifecycle tests do not prove that native applications recognize or execute installed skills. Use `loadout doctor --verbose` for the local component matrix.
 
 ## Command reference
 
@@ -414,16 +516,17 @@ Start at the top and stop whenever Loadout does everything you need.
 |       12 | Shows candidates waiting for deeper review                      | `loadout review-queue`                                       |
 |       13 | Lists MCP recipes and credential needs                          | `loadout mcp-recipe`; `loadout mcp-recipe --credential-free` |
 |       14 | Previews an MCP configuration                                   | `loadout mcp-recipe playwright --agent claude-code`          |
-|       15 | Recommends the right model and agent for a task                 | `loadout route design the auth system`                       |
-|       16 | Shows the full model catalog with pricing                       | `loadout route --models`; `loadout route --cost`             |
-|       17 | Sends a task to another agent via file-based handoff            | `loadout handoff send codex "write tests for auth"`          |
-|       18 | Checks agent health, permissions, and setup                     | `loadout doctor`; `loadout doctor --verbose`                 |
-|       19 | Lists and installs isolated runtime tools such as Graphify      | `loadout tool`; `loadout tool graphify`                      |
-|       20 | Lists snapshots or restores the latest managed change           | `loadout rollback --list`; `loadout rollback`                |
-|       21 | Previews removal of one managed package                         | `loadout remove <package-id>`                                |
-|       22 | Previews complete removal of Loadout-managed state              | `loadout uninstall`                                          |
-|       23 | Enables read-only daily discovery and update checks             | `loadout autopilot --yes`                                    |
-|       24 | Shows the complete CLI                                          | `loadout --help`; `loadout advanced`                         |
+|       15 | Installs Loadout's own skill into your agents                   | `loadout skills install loadout-router --yes`                |
+|       16 | Recommends the right model and agent for a task                 | `loadout route design the auth system`                       |
+|       17 | Shows the full model catalog with pricing                       | `loadout route --models`; `loadout route --cost`             |
+|       18 | Sends a task to another agent via file-based handoff            | `loadout handoff codex "write tests for auth"`               |
+|       19 | Checks agent health, permissions, and setup                     | `loadout doctor`; `loadout doctor --verbose`                 |
+|       20 | Lists and installs isolated runtime tools such as Graphify      | `loadout tool`; `loadout tool graphify`                      |
+|       21 | Lists snapshots or restores the latest managed change           | `loadout rollback --list`; `loadout rollback`                |
+|       22 | Previews removal of one managed package                         | `loadout remove <package-id>`                                |
+|       23 | Previews complete removal of Loadout-managed state              | `loadout uninstall`                                          |
+|       24 | Enables read-only daily discovery and update checks             | `loadout autopilot --yes`                                    |
+|       25 | Shows the complete CLI                                          | `loadout --help`; `loadout advanced`                         |
 
 Most mutating commands are dry runs first. After reading the preview, add `--yes` to
 apply. Commands with executable or connection risk require the additional approval