@erclx/aitk 3.49.0 → 3.51.0

package/claude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "aitk",
   "description": "Automated governance, versioning, and discovery tools for Claude Code.",
-  "version": "3.49.0",
+  "version": "3.51.0",
   "author": {
     "name": "Eric Le",
     "url": "https://github.com/erclx"

package/claude/skills/claude-autoship/SKILL.md

@@ -97,12 +97,30 @@ If all UI changes are covered by e2e tests, continue.
 
 ## Step 5: review
 
-Classify the diff first. Take the union of `git diff --name-only <base>` and `git ls-files --others --exclude-standard`, resolving `<base>` per Diff baseline. The classifier reads names only.
+Classify the diff first. Take the union of `git diff --name-only <base>` and `git ls-files --others --exclude-standard`, resolving `<base>` per Diff baseline, then hand that set to the verb rather than reading it against the list below yourself:
+
+```bash
+aitk autoship classify --json <path>...
+```
+
+The verb reads names only and touches git not at all, so the set stays the one this step already computed and no second baseline resolves to disagree with the first. Branch on the record's `decision` rather than on the exit code, which a shell function wrapping `aitk` can flatten to zero.
+
+- `skip`. Every path reads as prose and none states agent behavior. Skip review entirely and continue to Step 7.
+- `review`. Invoke `aitk:claude-review`. The record names the `file` that decided it and the `test` it failed, `extension` for a path that is not prose and `behavior-path` for prose that states what an agent does.
+- `refused`, carrying reason `no-changes`. The changed set was empty, so take the stop below.
+
+Say in the run which of the two decided, the verb or the written fallback, since a reader otherwise cannot tell a classification from a judgment.
 
 An empty list stops the chain: `❌ No changed files to classify. Re-run when the plan has yet to produce its output. When the output is gitignored by design, autoship cannot ship it, so take the work out of the chain.` An empty list satisfies the prose-only test vacuously, so reading it as prose-only routes the branch past review instead of through it.
 
 The two causes want different responses. A plan that has yet to produce its output is a re-run once it has. A plan whose output is gitignored by design, such as a read pass writing to `.claude/.tmp/`, is work the chain cannot carry at all, since `git-stage` finds nothing to commit six steps later. Never advise removing the output from `.gitignore`, which trades a stopped run for scratch committed into the repository.
 
+### When the verb is absent
+
+The verb ships with the CLI and this body ships with the plugin, so a target holding an older binary meets a missing subcommand. Apply the written test by hand there, and say the fallback decided it.
+
+Never read an absent subcommand as a skip. Failing open is the exact defect the verb closes, and a shell that answers `command not found` reaching a body that skips on anything other than a `skip` record would ship every branch unreviewed.
+
 The skip needs both tests to pass: every changed file matches `*.md` or `*.txt`, and no changed file sits under a behavior path. On a pass, skip review entirely and continue to Step 7. Otherwise invoke `aitk:claude-review`.
 
 Behavior paths carry two spellings, the one a surface authors at and the one it reaches a session at, so the rule reads the same in a toolkit and in a project that consumed one:
@@ -120,6 +138,8 @@ Informational prose is already gated by `docs-sync`, `claude-standards-audit`, a
 
 The list covers this toolkit's authoring layout and the layout it installs, which is not every layout. A project keeping executable prose where neither spelling reaches adds the path, and until it does every branch touching it skips review silently.
 
+The verb reads the same set from `src/autoship/paths.ts`, so a path added here belongs there too and a path added there belongs here. Two copies is what the fallback costs, and it stands until a release retires the written half.
+
 ## Step 6: evaluate findings
 
 Skip this step when Step 5 skipped review. Otherwise read `.claude/review/branch/review-<slug>.md` at the main worktree root. Split every finding by origin before parsing the summary line (`X critical, Y should-fix, Z minor`), since the stop exists for a defect the branch inherited rather than for one this run introduced.

package/docs/agents/commands.md

@@ -29,7 +29,7 @@ Full help: `aitk <command> --help`. Behavior notes for the install and sync verb
 | `aitk tasks archive`       | Move a shipped task off the board, clear its ordering row, and regenerate the index                                                                                   |
 | `aitk tasks pull-request`  | Record a pull request number on the task a branch closes, by stem or `--plan` (`--json`)                                                                              |
 | `aitk tasks outcome`       | Mark outcomes `[x]` on a task by position, repeating `--close` (`--json`)                                                                                             |
-| `aitk tasks validate`      | Report board rows whose plan, task file, group, file set, or blocker does not hold (`--json`)                                                                         |
+| `aitk tasks validate`      | Report board rows whose shape, order, plan, task file, group, file set, or blocker does not hold (`--json`)                                                           |
 | `aitk intake list`         | Report intake folder counts, or one folder's items, keeping what is unread with `--unread` (`--json`)                                                                 |
 | `aitk intake answer`       | Write selections into one cluster's answer slots, repeating `--set <item>=<answer>` (`--json`)                                                                        |
 | `aitk teach list`          | Report learning workspaces and the ordinal a new one takes, or what one workspace holds (`--json`)                                                                    |
@@ -60,6 +60,7 @@ Full help: `aitk <command> --help`. Behavior notes for the install and sync verb
 | `aitk deps audit`          | Report published advisories against the resolved dependency set, refusing rather than reporting clean when the index is unreachable (`--json`)                        |
 | `aitk labels audit`        | Report the labels a changed set earns from the pull request label map and the paths no row reaches (`--json`)                                                         |
 | `aitk labels scan`         | Fail a pull request whose title or body carries a phase label, sorting a release pull request's tokens as semver rather than as a leak (`--event`, `--json`)          |
+| `aitk autoship classify`   | Decide whether a changed set needs the review pass, naming the file and the test that decided it (`--json`)                                                           |
 | `aitk census [path]`       | Report tracked file count, a breakdown by extension, and a line total that skips whatever reads as binary (`--json`)                                                  |
 | `aitk audits run`          | Run every audit as one set, report per check under one verdict, and compare each count to the recorded baseline (`--json`, `--record`)                                |
 | `aitk audits list`         | List every audit the set runs, with the corpus each reads and whether it gates (`--json`)                                                                             |
@@ -113,6 +114,7 @@ Each domain exposes a consistent shape where applicable: `list`, `install`, `syn
 | `secrets`   | `scan`                                                                                                                                |
 | `deps`      | `audit`                                                                                                                               |
 | `labels`    | `audit`                                                                                                                               |
+| `autoship`  | `classify`                                                                                                                            |
 | `audits`    | `run`, `list`                                                                                                                         |
 
 Common patterns:

package/docs/agents/index.md

@@ -27,6 +27,7 @@ CLI catalog and invocation rules for agents, split by command domain. Start with
 - [Overview](overview.md): What this folder covers, the invocation rules every command inherits, and where domain behavior is documented instead
 - [Records](records.md): Validating the session records under .claude/ and the standards corpus, the per-kind checks, the refusal reasons, migrating a record a frontmatter change orphaned, reading each folder's size and growth, backing the folders to a private remote, and which root each kind defaults to
 - [Restated instructions](restated.md): Counting the instructions the always-loaded file and every path-scoped rule share with the seed, the shipped skill bodies, and each other, how a match is decided, the three classes, which surface a later edit starts from, and why the sweep reports rather than gates
+- [Review classification](review-classification.md): Deciding whether a changed set needs the review pass, the two tests it runs, why an empty set refuses rather than skipping, and the written fallback a target on an older binary falls back to
 - [Routing report](routing.md): Reading per CLAUDE.md section how many bullets name a path, what counts as naming one, when a rule counts as covering it, the two refusals, and why the verb reports rather than gates
 - [Rule citations](rule-citations.md): Resolving every path a governance rule cites and every frontmatter glob the internal corpus declares, the three forms a citation is written in, the shapes that look like citations and are not, the two classes where an absent path is correct, why the glob half reads one corpus, and why this one gates
 - [Sandbox](sandbox.md): Scenario routing, the expectation scoring surface, and the coverage census over scenarios and skills

package/docs/agents/review-classification.md

@@ -0,0 +1,77 @@
+---
+title: Review classification
+description: Deciding whether a changed set needs the review pass, the two tests it runs, why an empty set refuses rather than skipping, and the written fallback a target on an older binary falls back to
+---
+
+# Review classification
+
+`aitk autoship classify` answers the one decision the ship chain used to make by reading a bulleted list out of a skill body. It takes the names a branch changed and returns whether the review pass can be skipped, which file decided it, and which of the two tests that file failed.
+
+```bash
+aitk autoship classify docs/index.md README.md
+aitk autoship classify --json .claude/skills/deploy-check/SKILL.md
+```
+
+| Option   | Behavior                                                   |
+| -------- | ---------------------------------------------------------- |
+| `--json` | Add a machine-readable record on stdout, keeping the frame |
+
+Positional paths are the whole input. The verb never touches git, so it reads no baseline of its own and the caller hands over the set it already computed. A second read here could resolve a different range than the one the chain measured, which is the stale-baseline failure a prior row closed.
+
+Under `--json` the record holds stdout alone and the frame still renders on stderr, refusals included, which is the split `output-shape.md` fixes for every mode.
+
+## The two tests
+
+A branch skips review only when both hold across every changed name:
+
+- **Every path reads as prose.** The extension is `.md` or `.txt`, compared lowercased. Anything else is code, a config, or an asset.
+- **No path sits under a behavior path.** Markdown under one of those surfaces states what an agent does, so a change there is a behavior change wearing a prose extension.
+
+One failing file sends the whole branch to review. Documentation shipped beside a behavior change does not cancel it.
+
+The record names the first file to fail, tested in the caller's own order, and each file is read for its extension before its path. A set failing both tests reports one file and one test, which is all a caller needs to route.
+
+## The behavior paths
+
+Most carry two spellings, the one a surface authors at and the one it reaches a session at, so the rule reads the same in this toolkit and in a project that consumed one.
+
+| Surface           | Spellings                             |
+| ----------------- | ------------------------------------- |
+| Plugin skills     | `claude/skills/`, `.claude/skills/`   |
+| Governance rules  | `governance/rules/`, `.claude/rules/` |
+| Standards         | `standards/`                          |
+| Snippets          | `snippets/`                           |
+| Internal and seed | `internal/`, `tooling/`               |
+| Root instructions | `CLAUDE.md`                           |
+
+`standards/` and `snippets/` carry one spelling apiece. Neither installs into a project, reaching a reader by resolution and through the `claude/snippets` symlink respectively, so there is no consumed copy to name.
+
+`CLAUDE.md` is matched as a whole path rather than as a prefix, because a prefix reaches nothing that sits in no folder. A nested `docs/CLAUDE.md` stays informational.
+
+The set is data at `src/autoship/paths.ts`. That makes it permanently exempt from any later design that folds a machine-parsed list back into the surface citing it, per the machine-parsed clause in `.claude/ARCHITECTURE.md`.
+
+## Exit codes and refusals
+
+| Code | Meaning                                                      |
+| ---- | ------------------------------------------------------------ |
+| `0`  | prose-only, so the review pass can be skipped                |
+| `1`  | refused, with `reason` naming the cause                      |
+| `2`  | review is needed, with `file` and `test` naming what decided |
+
+Branch on the record's `decision` rather than on the exit code. A shell function wrapping `aitk` takes its status from whatever it runs last, so every non-zero exit can reach a caller as zero.
+
+An empty set refuses with `no-changes` rather than skipping. Both tests are universally quantified, so an empty set satisfies them vacuously, and reading that as prose-only would route a branch past review for having produced no output at all.
+
+## Why it is a verb
+
+The decision was three sentences in `claude-autoship` Step 5, applied by a session reading a bulleted list of paths. It failed three times. A driven arm on 2026-08-30 staged `.claude/skills/deploy-check/SKILL.md`, which that list names, and the chain skipped review and opened a draft pull request anyway. The rule was correct and the session did not apply it, and the two fixes before that one were each a rewrite of the same prose.
+
+A rule a session can talk itself out of moves into a verb. That is the same argument the quiz-order draw in `aitk teach lesson` was decided on: an instruction is a hope where a verb is a check.
+
+## The written fallback
+
+The verb ships with the CLI and Step 5 ships with the plugin, so a target holding an older binary meets a missing subcommand. The skill body keeps the written list and applies it by hand there, naming which of the two decided the run.
+
+The fallback is never a skip. Failing open is the exact defect the verb closes, so a body that skips on anything other than a `skip` record would ship every branch unreviewed the moment the subcommand went absent.
+
+Two copies of the path set is what the fallback costs, and it stands until a release retires the written half.

package/docs/agents/tasks.md

@@ -119,20 +119,26 @@ aitk tasks validate
 aitk tasks validate --json
 ```
 
-Five checks run. Plan and Collisions reach one half each of the `## Run now` test the board standard states. Mapping and Grouping test the folder contract and hold for every group. Blockers reaches the rows outside `## Run now`:
+Seven checks run. Plan and Collisions reach one half each of the `## Run now` test the board standard states. Mapping and Grouping test the folder contract and hold for every group, and Shape holds for every group too, ahead of the four. Ordering reaches only the `## Needs a plan` rows, and Blockers reaches every row outside `## Run now`:
 
-| Check      | What it reports                                                                      |
-| ---------- | ------------------------------------------------------------------------------------ |
-| Plan       | A `## Run now` row whose Plan column carries no link, or one resolving to no file    |
-| Mapping    | A row or backlog line naming no task file, and a task file neither surface names     |
-| Grouping   | A task carrying a row in more than one readiness group, or on both surfaces          |
-| Collisions | Two `## Run now` rows whose Touches columns name a path in common                    |
-| Blockers   | A parked row whose blocker has stopped holding, or whose cited task resolves nowhere |
+| Check      | What it reports                                                                                                      |
+| ---------- | -------------------------------------------------------------------------------------------------------------------- |
+| Shape      | A row whose cell count disagrees with its table's header, or one stranded behind a table a blank line already closed |
+| Plan       | A `## Run now` row whose Plan column carries no link, or one resolving to no file                                    |
+| Mapping    | A row or backlog line naming no task file, and a task file neither surface names                                     |
+| Grouping   | A task carrying a row in more than one readiness group, or on both surfaces                                          |
+| Ordering   | A `## Needs a plan` row whose stated position disagrees with where it actually sits                                  |
+| Collisions | Two `## Run now` rows whose Touches columns name a path in common                                                    |
+| Blockers   | A parked row whose blocker has stopped holding, or whose cited task resolves nowhere                                 |
+
+Shape runs before any other check reads a row, since a row failing it carries no dependable fields for the rest to check. A blank or prose line closes the table above it, so the walk treats the next pipe line as a fresh header candidate rather than as a continuation. That candidate counts as a header only when the line behind it is a separator carrying the same cell count, and one that fails is `row-untabled`, stranded behind a table that already closed. Cell count still has to match the header on every row that clears that test, and a row whose count disagrees is `row-misshapen`, the shape a dropped pipe or a merged column produces.
 
 Mapping spans two surfaces, because a task sits on `priority.md` when it would plausibly be planned soon and on `backlog.md` otherwise. A task file either surface names is accounted for, a file neither names is `row-missing`, and a file both name is `row-duplicated` for the reason a task in two groups is: it claims two things about itself and only one can hold. One check across both is what lets a task move between them without the move reading as a dropped file.
 
 A backlog line is a bullet carrying a link to a sibling task, since the backlog is a flat unordered list rather than a table. A bullet holding prose is skipped rather than reported, which keeps the file's own intro out of the findings, and the task that bullet meant to name is still reported as reaching neither surface. A project carrying no `backlog.md` reads as an empty backlog rather than a refusal, which leaves the one-to-one mapping this check ran before the second surface existed.
 
+Ordering reads only a `## Needs a plan` row whose `Waiting on` cell states a position at all. That phrase is prose rather than data, searched for anywhere in the cell rather than at its start, since every live row states its position at the end of a sentence rather than at the front. The vocabulary stops at `first` through `twentieth` plus `last`, since a parser strict enough to catch a gap would otherwise flag a row phrased correctly and differently, and bounding it to those words is what keeps a cell reading `Untestable from here` from matching on `from`. A row that does state a position is checked against where it actually sits, and that one comparison catches a gap, a duplicate, and a sequence starting somewhere other than first alike.
+
 The collision check is the one a person cannot run by eye. Paths come from the backticked spans in the Touches column, a span naming no file is dropped, and a directory collides with any file beneath it. A `## Run now` row whose column parses to nothing is reported rather than skipped, since a row stating no file set makes a claim nothing can check.
 
 Where a directory holds the other row's file, the finding names the row that claimed it, reading `both touch src/tasks, which v2.0-second claims as a folder.` The shared strings alone leave an over-broad cell and a genuine overlap identical, which is how a correct report was once read as the verb comparing folders rather than files.

package/docs/ai-workflow.md

@@ -113,7 +113,9 @@ The plans sweep reads the whole board rather than the tasks the session touched.
 
 `.claude/memory/` carries the same arrangement, its own hook regenerating `index.md` from each entry's `title`, `description`, and `category`. A hand-maintained `priority.md` sits beside it carrying execution order and what each task is waiting on, which the alphabetical index cannot express.
 
-`aitk tasks validate` checks what those rows claim against what the tree holds: every plan pointer resolves, every task file is named by a board row or a backlog line and never by both, no task sits in two groups, and no two rows marked ready touch the same file. One check across both surfaces is what lets a task move between the board and the backlog without the move reading as a dropped file. That fourth check is the half a reader cannot run by eye, and it is what keeps two workers from being handed colliding work. A fifth re-takes what a parked row waits on, reporting one whose cited task reached the trunk and one whose cited file nothing running still holds. A cited task settles the row by being archived, or by closing every outcome and naming a pull request the trunk carries, since the checkbox alone is marked while the branch is still in review. Both halves read a citation out of the blocker cell, so a row citing neither is reported as untested rather than counted clean, and so is a cited task the trunk could not answer for. It reports and never writes, because a row is the orchestrator's claim and a validator repairing one would assert the claim it exists to test. Nothing fires it automatically, since the board is gitignored per-machine scratch with no shared moment to hang a hook on, so the orchestrator's sweep calls it at the point the readiness claim is made and follows it with the parked re-test.
+`aitk tasks validate` reads a row against its own table before it reads anything the row claims. A blank or prose line closes the table above it, so a row stranded there is checked against the line behind it rather than parsed as a continuation, and a row that clears that test still has its cell count checked against its header. A `## Needs a plan` row that states its own position, searched for `<ordinal> here` or the bare word `last` anywhere in the cell rather than at its start, is checked against where it actually sits, which is what catches a gap, a duplicate, and a sequence starting somewhere other than first alike.
+
+Past that shape, it checks what a surviving row claims against what the tree holds: every plan pointer resolves, every task file is named by a board row or a backlog line and never by both, no task sits in two groups, and no two rows marked ready touch the same file. One check across both surfaces is what lets a task move between the board and the backlog without the move reading as a dropped file. The collision check is the half a reader cannot run by eye, and it is what keeps two workers from being handed colliding work. Blockers re-takes what a parked row waits on, reporting one whose cited task reached the trunk and one whose cited file nothing running still holds. A cited task settles the row by being archived, or by closing every outcome and naming a pull request the trunk carries, since the checkbox alone is marked while the branch is still in review. Both halves read a citation out of the blocker cell, so a row citing neither is reported as untested rather than counted clean, and so is a cited task the trunk could not answer for. It reports and never writes, because a row is the orchestrator's claim and a validator repairing one would assert the claim it exists to test. Nothing fires it automatically, since the board is gitignored per-machine scratch with no shared moment to hang a hook on, so the orchestrator's sweep calls it at the point the readiness claim is made and follows it with the parked re-test.
 
 `aitk:claude-tasks` owns the two operations that bracket a task's life. It creates the file, holding the filename convention and the frontmatter contract so a malformed write cannot break the index for every sibling, and it moves a shipped task to `.claude/tasks/archive/`. Creation is where the origin invariant is enforced: every task names a plan, a groundwork folder, an intake folder, or an issue, since a task with no origin is either lost context or work nobody decided to do.
 
@@ -144,6 +146,10 @@ Markdown under one states what an agent does, so a branch touching it reaches re
 
 An empty changed-file list stops the chain rather than counting as prose-only. The filename test passes vacuously on an empty set, which routed a branch past review instead of through it.
 
+`aitk autoship classify` answers that decision now, and the chain branches on the record it returns rather than on a session applying the list above. Three runs read past the list while it was prose, the last of them a driven arm that staged a file the list names and shipped a draft pull request with no review. The verb takes the names the chain already computed, so no second diff baseline resolves, and it names the file and the test that decided. [Review classification](agents/review-classification.md) carries the record shape and the exit codes.
+
+The list stays written in the skill body as the fallback for a target whose installed CLI predates the verb, since the two ship at different speeds. That fallback is never a skip: failing open is the defect the verb closes, so an absent subcommand routes to review rather than past it.
+
 #### Memory in the chain
 
 `git-ship` runs its verify gate and then opens on `claude-memory-capture`, which sends what the session learned to the surface that owns it. `autoship` reaches the same step by invoking that skill at its Step 7 rather than restating the order. A fact about a domain carrying an entry in `.claude/context/index.md` is routed to that entry, and `claude-docs` folds it in on the next step, so it ships in the same pull request. Anything no entry owns stays a file in `.claude/memory/`.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@erclx/aitk",
   "type": "module",
-  "version": "3.49.0",
+  "version": "3.51.0",
   "description": "Infrastructure and quality tooling for developer workflows",
   "license": "MIT",
   "bin": {

package/src/autoship/classify.ts

@@ -0,0 +1,75 @@
+import {
+  BEHAVIOR_FILES,
+  BEHAVIOR_PREFIXES,
+  PROSE_EXTENSIONS,
+} from '@/autoship/paths'
+
+/**
+ * Which of the two tests a file failed.
+ *
+ * Named apart rather than folded into one boolean, because the repair differs.
+ * A non-prose extension means the branch carries code and review is ordinary. A
+ * behavior path means prose that states what an agent does, which is the half
+ * three sessions read past.
+ */
+export type FailedTest = 'extension' | 'behavior-path'
+
+/** Why a classification produced no reading. */
+export type ClassifyRefusal = 'no-changes'
+
+export type Classification =
+  | { readonly kind: 'skip' }
+  | {
+      readonly kind: 'review'
+      readonly test: FailedTest
+      readonly file: string
+    }
+  | { readonly kind: 'refused'; readonly reason: ClassifyRefusal }
+
+/**
+ * Prefix-anchored against the folders, matching how `resolveCoverage` reads the
+ * label map, and equality against the whole paths a prefix cannot reach.
+ */
+function underBehaviorPath(path: string): boolean {
+  if (BEHAVIOR_FILES.some((file) => file === path)) return true
+  return BEHAVIOR_PREFIXES.some((prefix) => path.startsWith(prefix))
+}
+
+function readsAsProse(path: string): boolean {
+  const lowered = path.toLowerCase()
+  return PROSE_EXTENSIONS.some((extension) => lowered.endsWith(extension))
+}
+
+/**
+ * Decides whether a branch's changed set skips the review pass.
+ *
+ * The skip needs both tests to pass: every name reads as prose, and no name
+ * sits under a behavior path. One behavior file sends the whole branch to
+ * review, since documentation shipped beside a behavior change does not cancel
+ * it.
+ *
+ * An empty set refuses rather than skipping. Both tests are universally
+ * quantified, so an empty set satisfies them vacuously, and reading that as
+ * prose-only would route a branch past review for having produced no output at
+ * all.
+ *
+ * Names only. The caller hands the set the ship chain already computed, so no
+ * second baseline is read here and the stale-baseline half stays closed.
+ */
+export function classifyChanges(paths: readonly string[]): Classification {
+  if (paths.length === 0) return { kind: 'refused', reason: 'no-changes' }
+
+  // First failure in the caller's order wins, and each file is tested for its
+  // extension before its path. A set failing both tests reports one file and
+  // one test, which is all the branch needs to route.
+  for (const path of paths) {
+    if (!readsAsProse(path)) {
+      return { kind: 'review', test: 'extension', file: path }
+    }
+    if (underBehaviorPath(path)) {
+      return { kind: 'review', test: 'behavior-path', file: path }
+    }
+  }
+
+  return { kind: 'skip' }
+}

package/src/autoship/paths.ts

@@ -0,0 +1,51 @@
+/**
+ * The surfaces where markdown states what an agent does, and the extensions
+ * that read as prose, held as data one command parses.
+ *
+ * Lifted verbatim in content from the list `claude-autoship/SKILL.md` Step 5
+ * carried, which a session was asked to apply by hand. It failed that
+ * application three times, so the set moved here and the body now calls a verb
+ * that reads it. Being machine-parsed makes it permanently exempt from any
+ * later design that folds a standard back into the surface citing it, per the
+ * machine-parsed clause in `.claude/ARCHITECTURE.md`.
+ */
+
+/**
+ * Path prefixes under which a markdown change is a behavior change.
+ *
+ * Most carry two spellings, the one a surface authors at and the one it reaches
+ * a session at, so the rule reads the same in this toolkit and in a project
+ * that consumed one. `standards/` and `snippets/` carry one apiece: neither
+ * installs into a project, reaching a reader by resolution and through the
+ * `claude/snippets` symlink respectively, so no `.claude/` spelling exists to
+ * name.
+ */
+export const BEHAVIOR_PREFIXES = [
+  'claude/skills/',
+  '.claude/skills/',
+  'governance/rules/',
+  '.claude/rules/',
+  'standards/',
+  'snippets/',
+  'internal/',
+  'tooling/',
+] as const
+
+/**
+ * Behavior surfaces named as whole paths rather than as prefixes.
+ *
+ * A path prefix reaches nothing that sits in no folder, which is what the root
+ * instruction file is. Matching is equality rather than a suffix test, so a
+ * nested `docs/CLAUDE.md` stays informational the way the body's "at the
+ * repository root" qualifier says it should.
+ */
+export const BEHAVIOR_FILES = ['CLAUDE.md'] as const
+
+/**
+ * Extensions a changed file may carry for the branch to read as prose-only.
+ *
+ * Compared lowercased, so a `README.MD` is not routed to review for its
+ * spelling. Everything else is code, a config, or an asset, and one of them
+ * sends the whole branch to review.
+ */
+export const PROSE_EXTENSIONS = ['.md', '.txt'] as const

package/src/cli.ts

@@ -33,6 +33,7 @@ import { register as audits } from '@/commands/audits'
 import { register as secrets } from '@/commands/secrets'
 import { register as deps } from '@/commands/deps'
 import { register as labels } from '@/commands/labels'
+import { register as autoship } from '@/commands/autoship'
 import { register as census } from '@/commands/census'
 import { register as targets } from '@/commands/targets'
 import { register as upgrade } from '@/commands/upgrade'
@@ -80,6 +81,7 @@ function showHelp(): void {
     `${GREY}│${NC}    secrets [cmd]      ${GREY}# Read the shipped tree for credential-shaped values (scan)${NC}`,
     `${GREY}│${NC}    deps [cmd]         ${GREY}# Read the resolved dependency set for advisories (audit)${NC}`,
     `${GREY}│${NC}    labels [cmd]       ${GREY}# Read a changed set against the pull request label map (audit)${NC}`,
+    `${GREY}│${NC}    autoship [cmd]     ${GREY}# Decide whether a changed set needs the review pass (classify)${NC}`,
     `${GREY}│${NC}    census [path]      ${GREY}# Report tracked file count, extension breakdown, and line totals${NC}`,
     `${GREY}│${NC}    audits [cmd]       ${GREY}# Run every health check as one set (run, list)${NC}`,
     `${GREY}│${NC}    upgrade            ${GREY}# Reinstall the CLI globally with the manager that installed it${NC}`,
@@ -181,6 +183,7 @@ worktrees(program)
 secrets(program)
 deps(program)
 labels(program)
+autoship(program)
 census(program)
 audits(program)
 upgrade(program)

package/src/commands/autoship.ts

@@ -0,0 +1,129 @@
+import type { Command } from 'commander'
+import {
+  type ClassifyRefusal,
+  type FailedTest,
+  classifyChanges,
+} from '@/autoship/classify'
+import { intro, logInfo, logStep, logWarn, outro, plural } from '@/ui'
+
+interface ClassifyOptions {
+  readonly json?: boolean
+}
+
+/** What a reader does about the one way the classification produced no reading. */
+const REFUSALS: Record<ClassifyRefusal, string> = {
+  'no-changes':
+    'No changed files were supplied, so there is no set to classify. Pass the set the ship chain already computed.',
+}
+
+/** Why each failed test sends the branch to review, in the reader's terms. */
+const TESTS: Record<FailedTest, string> = {
+  extension: 'is not prose, so this branch carries a change review reads',
+  'behavior-path':
+    'sits under a behavior path, so its prose states what an agent does',
+}
+
+export function register(program: Command): void {
+  const autoship = program
+    .command('autoship')
+    .description('Answer the decisions the ship chain used to make in prose')
+    .helpOption('-h, --help', 'Show this help message')
+
+  autoship
+    .command('classify')
+    .description('Decide whether a changed set needs the review pass')
+    .argument('[paths...]', 'Changed set to classify, as names')
+    .helpOption('-h, --help', 'Show this help message')
+    .option('--json', 'Add a machine-readable record on stdout')
+    .addHelpText(
+      'after',
+      [
+        '',
+        'Reads names only and never touches git, so the caller hands over the',
+        'set it already computed rather than paying for a second baseline that',
+        'can disagree with the first.',
+        '',
+        'The skip needs both tests to pass. Every name reads as prose, and no',
+        'name sits under a behavior path, which is where markdown states what',
+        'an agent does. One behavior file sends the whole branch to review,',
+        'since documentation shipped beside a behavior change does not cancel',
+        'it.',
+        '',
+        'An empty set refuses rather than skipping. Both tests are universally',
+        'quantified, so an empty set satisfies them vacuously, and reading that',
+        'as prose-only would route a branch past review for producing no output.',
+        '',
+        'Exit codes:',
+        '  0  prose-only, so the review pass can be skipped',
+        '  1  refused, with the reason on stderr or in the JSON record',
+        '  2  review is needed, with the file and the test it failed named',
+        '',
+        'Examples:',
+        '  aitk autoship classify docs/index.md README.md',
+        '  aitk autoship classify --json .claude/skills/deploy-check/SKILL.md',
+        '',
+      ].join('\n'),
+    )
+    .action((paths: string[], opts: ClassifyOptions) => {
+      process.exitCode = runClassify(paths, opts)
+    })
+}
+
+function runClassify(paths: string[], opts: ClassifyOptions): number {
+  const emitJson = opts.json ?? false
+  const result = classifyChanges(paths)
+
+  intro('aitk autoship classify')
+
+  // The frame renders on stderr in both modes and the record goes to stdout
+  // alone, so an operator reading the terminal sees the refusal rather than a
+  // command that appeared to do nothing.
+  if (result.kind === 'refused') {
+    logStep('Refused')
+    logWarn(REFUSALS[result.reason])
+    outro()
+
+    if (emitJson) {
+      process.stdout.write(
+        `${JSON.stringify({
+          decision: 'refused',
+          reason: result.reason,
+          message: REFUSALS[result.reason],
+        })}\n`,
+      )
+    }
+    return 1
+  }
+
+  logStep('Scope')
+  logInfo(`${plural(paths.length, 'path')} supplied by the caller`)
+
+  if (result.kind === 'skip') {
+    logStep('Prose only')
+    logInfo('every path reads as prose and none states agent behavior')
+    outro()
+
+    if (emitJson) {
+      process.stdout.write(
+        `${JSON.stringify({ decision: 'skip', changed: paths })}\n`,
+      )
+    }
+    return 0
+  }
+
+  logStep('Review')
+  logWarn(`${result.file} ${TESTS[result.test]}.`)
+  outro()
+
+  if (emitJson) {
+    process.stdout.write(
+      `${JSON.stringify({
+        decision: 'review',
+        test: result.test,
+        file: result.file,
+        changed: paths,
+      })}\n`,
+    )
+  }
+  return 2
+}

package/src/tasks/validate.ts

@@ -37,6 +37,9 @@ export const FINDING_KINDS = [
   'task-unresolved',
   'row-missing',
   'row-duplicated',
+  'row-misshapen',
+  'row-untabled',
+  'row-misordered',
   'touches-unstated',
   'touches-collided',
   'blocker-settled',
@@ -95,6 +98,8 @@ export interface BoardRow {
   readonly touches: readonly string[] | undefined
   /** Absent when the group fixes no `Waiting on` column, which is `## Run now`. */
   readonly waiting: string | undefined
+  /** The ordinal phrase a `Waiting on` cell states about its own position, undefined when the cell carries none. */
+  readonly ordinal: OrdinalWord | 'last' | undefined
 }
 
 export interface ValidateReport {
@@ -216,23 +221,107 @@ function isGroup(heading: string): heading is BoardGroup {
   return (BOARD_GROUPS as readonly string[]).includes(heading)
 }
 
+const ORDINAL_WORDS = [
+  'first',
+  'second',
+  'third',
+  'fourth',
+  'fifth',
+  'sixth',
+  'seventh',
+  'eighth',
+  'ninth',
+  'tenth',
+  'eleventh',
+  'twelfth',
+  'thirteenth',
+  'fourteenth',
+  'fifteenth',
+  'sixteenth',
+  'seventeenth',
+  'eighteenth',
+  'nineteenth',
+  'twentieth',
+] as const
+
+type OrdinalWord = (typeof ORDINAL_WORDS)[number]
+
+const ORDINAL_HERE = new RegExp(
+  `\\b(${ORDINAL_WORDS.join('|')})\\s+here\\b`,
+  'i',
+)
+const LAST_AT_END = /\blast\.?\s*$/i
+
+/**
+ * Reads the ordinal phrase a `Waiting on` cell states about its own position,
+ * searching the whole cell for `<ordinal> here` or the bare word `last` rather
+ * than anchoring to where the cell opens. The phrase sits at the end of the
+ * sentence on every row that carries one, as in `nothing, cleared 2026-08-31
+ * when it merged. Third here`. The two-word phrase is safe to find anywhere,
+ * since it needs both a closed vocabulary word and `here` beside it, but a
+ * bare `last` is one of the commonest words in English and this corpus writes
+ * it constantly, as in `the last of the two instruments this rename needs`.
+ * Anchoring it to the end of the cell is what keeps that prose out of the
+ * findings, since every row that actually declares itself last puts the word
+ * there and nowhere else. A cell carrying neither reads as unordered rather
+ * than as an error, which keeps a legitimately-phrased row out of the
+ * findings.
+ */
+function readOrdinal(cell: string): OrdinalWord | 'last' | undefined {
+  const here = ORDINAL_HERE.exec(cell)
+  if (here?.[1]) return here[1].toLowerCase() as OrdinalWord
+
+  return LAST_AT_END.test(cell) ? 'last' : undefined
+}
+
+function isRowLine(line: string): boolean {
+  return line.trimStart().startsWith('|')
+}
+
+/**
+ * Whether a header candidate genuinely opens a table, meaning the line right
+ * behind it is a separator carrying the same cell count. A row landing where a
+ * blank line already closed the table above it looks identical to a fresh
+ * header until this read, since both are the first pipe line the walk has
+ * seen since the reset.
+ */
+function opensTable(
+  header: readonly string[],
+  next: string | undefined,
+): boolean {
+  if (next === undefined || !isRowLine(next)) return false
+  const cells = splitCells(next)
+  return isSeparator(cells) && cells.length === header.length
+}
+
 /**
  * Parses the ordering file into rows keyed by readiness group. Columns are read
  * from each table's own header rather than by position, so a group whose shape
  * differs from this repository's is reported for what it lacks instead of
  * having its second cell read as something it never was.
+ *
+ * The walk carries one more piece of state than a header: whether the table
+ * that header opened is still open. A blank or prose line closes it, so a row
+ * stranded behind that close is read as one candidate header among many rather
+ * than as a continuation of the table above, and each surviving row's cell
+ * count is checked against the header it actually followed.
  */
 export function readBoard(text: string): {
   readonly rows: readonly BoardRow[]
   readonly groups: readonly BoardGroup[]
+  readonly findings: readonly Finding[]
 } {
   const rows: BoardRow[] = []
   const groups: BoardGroup[] = []
+  const findings: Finding[] = []
+
+  const lines = text.split('\n')
 
   let group: BoardGroup | undefined
   let header: string[] | undefined
 
-  for (const line of text.split('\n')) {
+  for (let i = 0; i < lines.length; i += 1) {
+    const line = lines[i] ?? ''
     const heading = /^##\s+(.+?)\s*$/.exec(line)
     if (heading) {
       const title = heading[1]
@@ -242,16 +331,42 @@ export function readBoard(text: string): {
       continue
     }
 
-    if (!group || !line.trimStart().startsWith('|')) continue
+    if (!group) continue
+
+    if (!isRowLine(line)) {
+      header = undefined
+      continue
+    }
 
     const cells = splitCells(line)
     if (isSeparator(cells)) continue
 
     if (!header) {
+      if (!opensTable(cells, lines[i + 1])) {
+        findings.push({
+          kind: 'row-untabled',
+          group,
+          subject: line.trim(),
+          message:
+            'sits outside a table. The table above it already closed at the line before it.',
+        })
+        continue
+      }
+
       header = cells
       continue
     }
 
+    if (cells.length !== header.length) {
+      findings.push({
+        kind: 'row-misshapen',
+        group,
+        subject: line.trim(),
+        message: `carries ${cells.length} cell(s) against the ${header.length}-cell header above it.`,
+      })
+      continue
+    }
+
     const taskAt = columnIndex(header, 'task')
     const planAt = columnIndex(header, 'plan')
     const touchesAt = columnIndex(header, 'touches')
@@ -260,6 +375,7 @@ export function readBoard(text: string): {
     const task = taskAt >= 0 ? (cells[taskAt] ?? '') : ''
     const target = linkTarget(task)
     const plan = planAt >= 0 ? linkTarget(cells[planAt] ?? '') : undefined
+    const waiting = waitingAt >= 0 ? (cells[waitingAt] ?? '') : undefined
 
     rows.push({
       group,
@@ -267,11 +383,46 @@ export function readBoard(text: string): {
       stem: target ? stemOf(target) : undefined,
       plan,
       touches: touchesAt >= 0 ? readPaths(cells[touchesAt] ?? '') : undefined,
-      waiting: waitingAt >= 0 ? (cells[waitingAt] ?? '') : undefined,
+      waiting,
+      ordinal: waiting ? readOrdinal(waiting) : undefined,
     })
   }
 
-  return { rows, groups }
+  return { rows, groups, findings }
+}
+
+/**
+ * Reports a `## Needs a plan` row whose stated ordinal disagrees with where it
+ * actually sits in that group. Reading the sequence for gaps and duplicates on
+ * its own would detect less, since row position is contiguous by
+ * construction, and a hand-renumbered sequence is exactly a case where the
+ * prose and the position have come apart.
+ */
+function checkOrdinals(rows: readonly BoardRow[]): Finding[] {
+  const findings: Finding[] = []
+  const parked = rows.filter((row) => row.group === 'Needs a plan')
+
+  parked.forEach((row, index) => {
+    if (!row.ordinal) return
+
+    const position = index + 1
+    const expected =
+      row.ordinal === 'last'
+        ? parked.length
+        : ORDINAL_WORDS.indexOf(row.ordinal) + 1
+
+    if (expected === position) return
+
+    const phrase = row.ordinal === 'last' ? 'last' : `${row.ordinal} here`
+    findings.push({
+      kind: 'row-misordered',
+      group: row.group,
+      subject: subjectOf(row),
+      message: `declares itself "${phrase}", but sits at position ${position} of ${parked.length} in ${row.group}.`,
+    })
+  })
+
+  return findings
 }
 
 /**
@@ -805,7 +956,11 @@ export async function validateBoard(
     return refuse('no-ordering', `No ordering file at ${ordering}.`)
   }
 
-  const { rows, groups } = readBoard(await readFile(ordering, 'utf8'))
+  const {
+    rows,
+    groups,
+    findings: shapeFindings,
+  } = readBoard(await readFile(ordering, 'utf8'))
 
   if (groups.length === 0) {
     return refuse(
@@ -826,9 +981,11 @@ export async function validateBoard(
   const parked = await checkParked(rows, root, trunk)
 
   const findings = [
+    ...shapeFindings,
     ...checkMapping(rows, backlog, stems, dir),
     ...checkPlans(rows, dir, root),
     ...checkCollisions(rows),
+    ...checkOrdinals(rows),
     ...parked.findings,
   ]