test(pstack): ban leftover spawn strings in the resource grep

skills/how/SKILL.md

@@ -60,7 +60,7 @@ Then proceed to Step 3.
 
 ### Step 2b. Direct Explain (simple questions)
 
-Spawn a single subagent subagent that explores and explains in one pass:
+Spawn a single subagent that explores and explains in one pass:
 
 - `agent`: `oracle`
 - omit `model` to use the configured oracle profile
@@ -71,7 +71,7 @@ Proceed to Step 4.
 
 ### Step 3. Synthesize (complex questions only)
 
-Once all explorers return, spawn a single subagent subagent to synthesize their findings into one coherent explanation:
+Once all explorers return, spawn a single subagent to synthesize their findings into one coherent explanation:
 
 - `agent`: `oracle`
 - omit `model` to use the configured oracle profile

skills/no-comments/SKILL.md

@@ -16,7 +16,7 @@ Use the caller's files or diff. Otherwise use the current diff against the base
 
 ## Steps
 
-1. Spawn `subagent` with `agent: "Comment Sicko"`. Pass the scope. Do not restate its rules.
+1. Spawn `subagent` with `agent: "comment-sicko"`. Pass the scope. Do not restate its rules.
 2. Inspect its report and diff. Reject application-code edits, scope escapes, exception-protected deletions, misstated `MUST KILL` reasons, and flags that treat kept intentional code as guilty. Reshape flags on our-code surprises stay actionable. Do not restore those comments. A keep survives only with proof it is about something we cannot change. Audit missed scoped lint and TypeScript suppressions. Correctness or safety suppressions stay actionable `MUST KILL`s. Restore deletions only with exact exceptions and scoped proof. Before accepting thin `IMPORTANT` or `do not remove` kills or keeps, run `/skill:how` or `/skill:why` on their symbol. If a kill is ambiguous, do not restore. If a keep is refuted or still ambiguous, delete it. Revert and rerun one rejected report with the failure named. Reject a second, report it open, and fail `/skill:no-comments`.
 3. Fix trivial accepted flags directly by deleting a dead path, dropping a parameter, or using the real API. If any fix needs a shape, run `/skill:architect` once for the accepted set and surrounding code. Stop at the sketch. Architect shapes. Step 4 implements.
 4. Implement the smallest root-cause fix in scope. Remove every named workaround. If the root cause is out of scope, land the smallest in-scope fix and report the rest open. The **principle-fix-root-causes** and **principle-redesign-from-first-principles** skills guide intent only: fix real causes, redesign as if requirements always existed, never bolt on symptom guards. Neither authorizes widening the fence nor fixing instances outside it.

test/resources/resources.test.mjs

@@ -120,11 +120,14 @@ test("active resources use Pi runtime contracts", async () => {
     ["symbolic model profile", /profile:(?:fast|reasoning|instruction|review)/],
     ["unsupported subagents.profiles", /subagents\.profiles/],
     ["unsupported read-write acceptance role", /acceptanceRole:\s*read-write/],
+    ["Comment Sicko spawn", /agent: "Comment Sicko"/],
+    ["doubled subagent", /subagent subagent/],
   ]) {
     assert.doesNotMatch(corpus, pattern, `${token} remains in active resources`);
   }
   const mode = await readFile(join(skillsDir, "poteto-mode", "SKILL.md"), "utf8");
   const how = await readFile(join(skillsDir, "how", "SKILL.md"), "utf8");
+  const noComments = await readFile(join(skillsDir, "no-comments", "SKILL.md"), "utf8");
   const recall = await readFile(join(skillsDir, "recall", "SKILL.md"), "utf8");
   const shipping = await readFile(
     join(skillsDir, "poteto-mode", "playbooks", "shipping.md"),
@@ -133,6 +136,7 @@ test("active resources use Pi runtime contracts", async () => {
   assert.match(mode, /workflowScript/);
   assert.match(how, /runs\.all/);
   assert.match(mode, /\bask\b/);
+  assert.match(noComments, /agent: "comment-sicko"/);
   assert.match(recall, /PI_SESSION_FILE/);
   assert.match(shipping, /gh stack/);
   assert.match(shipping, /Graphite/);