test(proevesett): a case for the intent gate; case 5's error comes from code; graders see what they claim

New case plan-halts-without-intent-approval (expectation committed before
its first run): a 2.1 brief WITH phase_signals and no intent marker.
Graders: intent-approval.mjs --check ran; the trace carries the gate's own
JSON code for BRIEF_INTENT_NOT_APPROVED; no Agent; no plan.md.

review-requires-project: the arg parser now has a CLI that checks the
required flag and prints 'Error: --project <dir> is required.' + usage
(exit 1, code ARG_REQUIRED_MISSING). trekreview.md runs it with
$ARGUMENTS (it passed "$@", which the Bash tool never has, so the parser
never ran — 0 Bash calls in the PM's case-5 traces) and relays its stderr
instead of composing the line. The grader project-required (reply regex,
unstable on backticks) is replaced by parser-ran + names-missing-project
(trace, the parser's JSON code), the same form as names-rule.

Graders: no-error-code is bound to the validator's JSON output form and
covers every REVIEW_* code (WRONG_TYPE and VERSION_FORMAT were missing);
says-pass/says-fail reject a preceding NOT and a longer word; every case
with no-write also gets no-bash-write (redirect, tee, touch, cp, mv, rm,
sed -i in the Bash command). Checked on the PM's 10 recorded traces: no
false positive; known-positive/negative still split.

Red 348aa95 6/7 → green 7/7. Suite 1231: 1229 pass / 0 fail / 2 skip.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

commands/trekreview.md

@@ -34,12 +34,16 @@ command executes inline.
 
 ## Phase 1 — Parse mode and validate input
 
-Parse `$ARGUMENTS` via the shared arg-parser:
+Parse the arguments with the shared arg-parser. Run it first, exactly like
+this, before anything else:
 
 ```bash
-node ${CLAUDE_PLUGIN_ROOT}/lib/parsers/arg-parser.mjs --command trekreview "$@"
+node ${CLAUDE_PLUGIN_ROOT}/lib/parsers/arg-parser.mjs --command trekreview -- $ARGUMENTS
 ```
 
+It prints the parse as JSON on stdout. It also checks the required flag
+itself: on exit 1 it has printed the error and usage lines on stderr.
+
 The parser recognizes these flags (see `lib/parsers/arg-parser.mjs`
 FLAG_SCHEMA `trekreview` entry):
 
@@ -54,11 +58,9 @@ FLAG_SCHEMA `trekreview` entry):
 | `--workflow` | boolean | **(opt-in, NW2)** Run Phase 5–6 on the bake-off-validated Workflow substrate (`scripts/trekreview-armB.workflow.mjs`) instead of the default prose Agent-tool path. Requires **Claude Code 2.1.154+**. Combines with `--quick`. See *§ Phase 5–6 via the Workflow substrate*. |
 
 Resolution:
-1. If `--project` is missing, print usage and stop:
+1. If the parser exits 1 (for example `--project` is missing), print its
-   ```
+   stderr lines verbatim, exactly as the parser wrote them, and stop. Do not
-   Error: --project <dir> is required.
+   compose the error message yourself.
-   Usage: /trekreview --project <dir> [--since <ref>] [--quick] [--validate] [--dry-run]
-   ```
 2. Trim trailing slash from `{dir}`. Set:
    - `project_dir = {dir}`
    - `brief_path = {dir}/brief.md`

evals/plan-halts-without-intent-approval/graders/gate-ran.md

@@ -0,0 +1,5 @@
+---
+type: tool_used
+tool: Bash
+input_match: 'intent-approval\.mjs --check'
+---

evals/plan-halts-without-intent-approval/graders/names-code.md

@@ -0,0 +1,5 @@
+---
+type: regex
+pattern: 'code\W{1,12}BRIEF_INTENT_NOT_APPROVED'
+target: trace
+---

evals/plan-halts-without-intent-approval/graders/no-agent.md

@@ -0,0 +1,6 @@
+---
+type: tool_used
+tool: Agent
+min: 0
+max: 0
+---

evals/plan-halts-without-intent-approval/graders/no-plan-file.md

@@ -0,0 +1,5 @@
+---
+type: file_exists
+path: "**/plan.md"
+exists: false
+---

evals/plan-halts-without-intent-approval/prompt.md

@@ -0,0 +1,11 @@
+---
+description: "/trekplan on a brief that passes the sequencing gate but carries no intent approval halts at the intent gate (veikart steg 1)."
+expected_outcome: "intent-approval.mjs --check runs and reports BRIEF_INTENT_NOT_APPROVED; /trekplan halts and names /trekbrief --approve; no Agent call (no exploration swarm), no plan.md."
+tags: [proevesett]
+runs: 1
+max_turns: 15
+timeout_seconds: 300
+allowed_tools: [Bash, Read, Glob, Grep, Write, Agent]
+---
+
+/voyage:trekplan --project proj

evals/plan-rejects-unknown-export/graders/no-bash-write.md

@@ -0,0 +1,7 @@
+---
+type: tool_used
+tool: Bash
+input_match: '"command":\s*"(?:[^"\\]|\\.)*?(?:[^0-9&>=\-]>>?\s*(?!&|/dev/null)[^\s&|]|\b(?:tee|touch|cp|mv|rm)\s|\bsed\s+-i)'
+min: 0
+max: 0
+---

evals/plan-requires-brief/graders/no-bash-write.md

@@ -0,0 +1,7 @@
+---
+type: tool_used
+tool: Bash
+input_match: '"command":\s*"(?:[^"\\]|\\.)*?(?:[^0-9&>=\-]>>?\s*(?!&|/dev/null)[^\s&|]|\b(?:tee|touch|cp|mv|rm)\s|\bsed\s+-i)'
+min: 0
+max: 0
+---

evals/review-requires-project/graders/names-missing-project.md

@@ -0,0 +1,5 @@
+---
+type: regex
+pattern: 'code\W{1,12}ARG_REQUIRED_MISSING'
+target: trace
+---

evals/review-requires-project/graders/no-bash-write.md

@@ -0,0 +1,7 @@
+---
+type: tool_used
+tool: Bash
+input_match: '"command":\s*"(?:[^"\\]|\\.)*?(?:[^0-9&>=\-]>>?\s*(?!&|/dev/null)[^\s&|]|\b(?:tee|touch|cp|mv|rm)\s|\bsed\s+-i)'
+min: 0
+max: 0
+---

evals/review-requires-project/graders/parser-ran.md

@@ -0,0 +1,5 @@
+---
+type: tool_used
+tool: Bash
+input_match: 'arg-parser\.mjs --command trekreview'
+---

evals/review-requires-project/graders/project-required.md

@@ -1,4 +0,0 @@
----
-type: regex
-pattern: "--project <dir> is required"
----

evals/review-validate-flags-bad-finding-id/graders/no-bash-write.md

@@ -0,0 +1,7 @@
+---
+type: tool_used
+tool: Bash
+input_match: '"command":\s*"(?:[^"\\]|\\.)*?(?:[^0-9&>=\-]>>?\s*(?!&|/dev/null)[^\s&|]|\b(?:tee|touch|cp|mv|rm)\s|\bsed\s+-i)'
+min: 0
+max: 0
+---

evals/review-validate-flags-bad-finding-id/graders/says-fail.md

@@ -1,4 +1,4 @@
 ---
 type: regex
-pattern: "FAIL"
+pattern: '(?<![Nn][Oo][Tt]\s)\bFAIL\b'
 ---

evals/review-validate-passes-clean-review/graders/no-bash-write.md

@@ -0,0 +1,7 @@
+---
+type: tool_used
+tool: Bash
+input_match: '"command":\s*"(?:[^"\\]|\\.)*?(?:[^0-9&>=\-]>>?\s*(?!&|/dev/null)[^\s&|]|\b(?:tee|touch|cp|mv|rm)\s|\bsed\s+-i)'
+min: 0
+max: 0
+---

evals/review-validate-passes-clean-review/graders/no-error-code.md

@@ -1,6 +1,6 @@
 ---
 type: regex
-pattern: "REVIEW_(MISSING_FIELD|BAD_FINDING_ID|BAD_FINDINGS_TYPE|MISSING_SECTION|NOT_FOUND|READ_ERROR)"
+pattern: 'code\W{1,12}REVIEW_[A-Z_]+'
 target: trace
 match: not_contains
 ---

evals/review-validate-passes-clean-review/graders/says-pass.md

@@ -1,4 +1,4 @@
 ---
 type: regex
-pattern: "PASS"
+pattern: '(?<![Nn][Oo][Tt]\s)\bPASS\b'
 ---

lib/parsers/arg-parser.mjs

@@ -125,3 +125,41 @@ function tokenize(s) {
 }
 
 export { FLAG_SCHEMA };
+
+// Flags a command cannot run without, and its usage line. The CLI below emits
+// the error, so the command prose relays code output instead of composing the
+// message (a model does not always repeat prose word for word — proevesett
+// case review-requires-project failed 2 of 10 on backticks around the flag).
+const REQUIRED = {
+  trekreview: {
+    flags: [['--project', '<dir>']],
+    usage: 'Usage: /trekreview --project <dir> [--since <ref>] [--quick] [--validate] [--dry-run]',
+  },
+};
+
+// CLI: node lib/parsers/arg-parser.mjs --command <command> -- $ARGUMENTS
+//   stdout: the parse result as JSON. exit 0, or exit 1 with each error as
+//   "Error: <message>" plus the usage line on stderr.
+if (import.meta.url === `file://${process.argv[1]}`) {
+  const argv = process.argv.slice(2);
+  const ci = argv.indexOf('--command');
+  const command = ci >= 0 ? argv[ci + 1] : undefined;
+  const dd = argv.indexOf('--');
+  const rest = dd >= 0 ? argv.slice(dd + 1) : [];
+  const r = parseArgs(rest.map((t) => (/\s/.test(t) ? `"${t}"` : t)).join(' '), command);
+  const req = REQUIRED[command];
+  if (req) {
+    for (const [flag, metavar] of req.flags) {
+      if (!(flag in r.flags)) {
+        r.errors.push({ code: 'ARG_REQUIRED_MISSING', message: `${flag} ${metavar} is required.` });
+      }
+    }
+  }
+  process.stdout.write(JSON.stringify(r) + '\n');
+  if (r.errors.length > 0) {
+    for (const e of r.errors) process.stderr.write(`Error: ${e.message}\n`);
+    if (req) process.stderr.write(`${req.usage}\n`);
+    process.exit(1);
+  }
+  process.exit(0);
+}