claude-dev-env 2.16.0 → 2.17.0

package/system-prompts/software-engineer.xml

@@ -7,6 +7,8 @@
 </role>
 
 <task_scope>
+  Apply rules/asd-ste100-language.md for user-facing word choice, sentence style, tone, punctuation,
+  and prose form. Keep the behavior contracts below within their named scope.
   Defer to the user's judgment when they indicate a task is too ambitious or complex to pursue.
   Match the scope of every action to what the user explicitly requested: a bug fix delivers the
   fix, a feature delivers the feature. Restrict scope statements to requirements, steps, and
@@ -20,11 +22,13 @@
 
   When a user asks a question, answer the question. When a user describes a problem, investigate
   and recommend. When the user says "do it", "go ahead", "make the change", or similarly
-  explicit language, proceed with action. When in doubt, ask: "Would you like me to make this
-  change, or just show you the approach?"
+  explicit language, proceed with action. Route user choices through AskUserQuestion.
 </task_scope>
 
 <output_style>
+  When a user-facing response needs beginner presentation, use ELI5: beginner framing, large
+  visuals, minimal text, one stable self-contained HTML artifact, update-in-place continuity,
+  and sharing. Apply rules/asd-ste100-language.md to sentence-level prose inside that artifact.
   Lead every response with the direct answer or result. Open with the substance — the
   conclusion, the fix, the decision — before any supporting context or explanation. Expand
   depth in proportion to the complexity of the ask: a direct question earns a sentence; a
@@ -387,7 +391,8 @@
   response begins with the outcome. When thinking is disabled, speak one brief
   natural-language sentence before a tool call that needs context, state when no
   fitting tool exists, and never emit internal-system XML in visible output.
-  Full contract: rules/opus5-communication-contract.md (opus5-communication-contract-v1).
+  Language policy: rules/asd-ste100-language.md. This section owns visible progress,
+  tool narration, and outcome-first final structure.
 </communication_contract>
 
 <help_and_feedback>

package/.agents/skills/grokify/evals/README.md

@@ -1,72 +0,0 @@
-# Grok capability evals (opt-in only)
-
-Live measurements of Grok Build capabilities used by the `grokify` skill wording.
-
-**Manual / opt-in only.** These evals never gate default `npm test`, pr-check, or CI.
-
-## Requirements
-
-- `grok` on `PATH` and authenticated (`grok models` exits 0). The runner calls `grok` by default; set `GROK_BIN` to point it at another binary.
-- Network access for the Grok API
-- A writable platform temp directory (`$env:TEMP` on Windows, `$TMPDIR` / `/tmp` elsewhere)
-- For E3, an agent `grok` can load under `--agent`. The runner passes the agent named by `GROK_CAPABILITY_EVAL_AGENT` (default `Explore`); set that variable to an agent your `grok` resolves when the default does not exist for you.
-
-## Run
-
-From the package root (`packages/claude-dev-env`):
-
-```powershell
-# Windows PowerShell
-$env:GROK_CAPABILITY_EVALS = "1"
-node skills/grokify/evals/run-capability-evals.mjs
-```
-
-```bash
-# POSIX
-GROK_CAPABILITY_EVALS=1 node skills/grokify/evals/run-capability-evals.mjs
-```
-
-From this skill folder (`packages/claude-dev-env/.agents/skills/grokify`):
-
-```powershell
-# Windows PowerShell
-$env:GROK_CAPABILITY_EVALS = "1"
-node evals/run-capability-evals.mjs
-```
-
-```bash
-# POSIX
-GROK_CAPABILITY_EVALS=1 node evals/run-capability-evals.mjs
-```
-
-Or pass `--run` without the env var (paths match the cwd above):
-
-```powershell
-# from package root
-node skills/grokify/evals/run-capability-evals.mjs --run
-# from this skill folder
-node evals/run-capability-evals.mjs --run
-```
-
-Without `GROK_CAPABILITY_EVALS=1` or `--run`, the script prints how to opt in and exits 0 (no live calls).
-
-## What it measures
-
-| Eval | Assertion |
-|------|-----------|
-| E1 | `can_spawn_subagent_tool === true` and tool list includes `spawn_subagent` |
-| E2 | `spawn_succeeded === true` (child reports `SPAWN_OK`) |
-| E3 | `skill_read_ok === true` and `agent_definition_loaded === true` (skill file read under `--agent`) |
-| E4 | Probe write under the eval cwd succeeds (soft: hooks log may show `global/settings` + `pre_tool_use`) |
-| E5 | `has_workflow_tool === false` and `result === "no_tool"` (both fields agree on absence) |
-
-Each live `grok` call uses a unique `--leader-socket` under a fresh temp directory so concurrent runs do not share a socket.
-
-## Offline static guard
-
-`../capability-claims.test.mjs` runs under package `npm test` (no live `grok`):
-
-- `SKILL.md` must not contain `cannot spawn Claude subagents`
-- `SKILL.md` and the handoff template must still mention `claude -p` for the advisor path
-
-`parse-payload.test.mjs` also runs under package `npm test` (no live `grok`): it unit-tests the runner's output parser (`tryParseJsonObject`, `extractResultText`, `parsePayload`, `isWorkflowToolAbsent`).

package/.agents/skills/grokify/evals/parse-payload.test.mjs

@@ -1,171 +0,0 @@
-import { test } from 'node:test';
-import { strict as assert } from 'node:assert';
-import {
-  tryParseJsonObject,
-  extractResultText,
-  parsePayload,
-  isWorkflowToolAbsent,
-} from './run-capability-evals.mjs';
-
-const E1_CLAIM_PAYLOAD = {
-  can_spawn_subagent_tool: true,
-  tool_names: ['spawn_subagent'],
-  agents_dir_exists: true,
-  skills_dir_exists: true,
-};
-
-test('tryParseJsonObject parses a pure JSON object string', () => {
-  const parsed = tryParseJsonObject(JSON.stringify(E1_CLAIM_PAYLOAD));
-  assert.deepEqual(parsed, E1_CLAIM_PAYLOAD);
-});
-
-test('tryParseJsonObject strips leading prose before the first brace', () => {
-  const withProse = `Here is the inventory:\n${JSON.stringify(E1_CLAIM_PAYLOAD)}`;
-  const parsed = tryParseJsonObject(withProse);
-  assert.deepEqual(parsed, E1_CLAIM_PAYLOAD);
-});
-
-test('tryParseJsonObject extracts the object when trailing prose carries braces', () => {
-  const withTrailingBraces = `${JSON.stringify(E1_CLAIM_PAYLOAD)}\nNote: see {run-directory} for logs.`;
-  const parsed = tryParseJsonObject(withTrailingBraces);
-  assert.deepEqual(parsed, E1_CLAIM_PAYLOAD);
-});
-
-test('tryParseJsonObject ignores a stray brace pair in leading prose', () => {
-  const withLeadingBraces = `Here is the result (see {} for details):\n${JSON.stringify(E1_CLAIM_PAYLOAD)}`;
-  const parsed = tryParseJsonObject(withLeadingBraces);
-  assert.deepEqual(parsed, E1_CLAIM_PAYLOAD);
-});
-
-test('tryParseJsonObject returns null for empty input', () => {
-  assert.equal(tryParseJsonObject(''), null);
-  assert.equal(tryParseJsonObject('   '), null);
-});
-
-test('extractResultText reads Grok top-level text field', () => {
-  const nestedJson = JSON.stringify(E1_CLAIM_PAYLOAD);
-  const envelope = JSON.stringify({ text: nestedJson, model: 'grok' });
-  assert.equal(extractResultText(envelope), nestedJson);
-});
-
-test('extractResultText prefers Claude result over Grok text', () => {
-  const envelope = JSON.stringify({
-    result: '{"from":"result"}',
-    text: '{"from":"text"}',
-  });
-  assert.equal(extractResultText(envelope), '{"from":"result"}');
-});
-
-test('extractResultText prefers Grok text over a conversational message', () => {
-  const envelope = JSON.stringify({
-    message: 'working',
-    text: '{"from":"text"}',
-  });
-  assert.equal(extractResultText(envelope), '{"from":"text"}');
-});
-
-test('extractResultText reads Claude message field', () => {
-  const envelope = JSON.stringify({ message: '{"from":"message"}' });
-  assert.equal(extractResultText(envelope), '{"from":"message"}');
-});
-
-test('extractResultText reads Claude stream result events', () => {
-  const envelope = JSON.stringify([
-    { type: 'assistant', content: 'thinking' },
-    {
-      type: 'result',
-      result: JSON.stringify(E1_CLAIM_PAYLOAD),
-    },
-  ]);
-  assert.equal(extractResultText(envelope), JSON.stringify(E1_CLAIM_PAYLOAD));
-});
-
-test('extractResultText prefers the last result event in a stream array', () => {
-  const intermediateClaim = { can_spawn_subagent_tool: false, tool_names: [] };
-  const envelope = JSON.stringify([
-    { type: 'assistant', content: 'thinking' },
-    { type: 'result', result: JSON.stringify(intermediateClaim) },
-    { type: 'assistant', content: 'retry' },
-    { type: 'result', result: JSON.stringify(E1_CLAIM_PAYLOAD) },
-  ]);
-  assert.equal(extractResultText(envelope), JSON.stringify(E1_CLAIM_PAYLOAD));
-});
-
-test('parsePayload extracts nested claim JSON from Grok text envelope', () => {
-  const envelope = JSON.stringify({
-    text: JSON.stringify(E1_CLAIM_PAYLOAD),
-  });
-  const payload = parsePayload(envelope);
-  assert.equal(payload.can_spawn_subagent_tool, true);
-  assert.deepEqual(payload.tool_names, ['spawn_subagent']);
-});
-
-test('parsePayload extracts nested claim JSON when Grok text has leading prose', () => {
-  const envelope = JSON.stringify({
-    text: `Capability inventory complete.\n${JSON.stringify(E1_CLAIM_PAYLOAD)}`,
-  });
-  const payload = parsePayload(envelope);
-  assert.equal(payload.can_spawn_subagent_tool, true);
-  assert.equal(payload.agents_dir_exists, true);
-});
-
-test('parsePayload still reads Claude result envelopes', () => {
-  const envelope = JSON.stringify({
-    result: JSON.stringify(E1_CLAIM_PAYLOAD),
-  });
-  const payload = parsePayload(envelope);
-  assert.equal(payload.can_spawn_subagent_tool, true);
-});
-
-test('parsePayload still reads Claude message envelopes', () => {
-  const envelope = JSON.stringify({
-    message: JSON.stringify(E1_CLAIM_PAYLOAD),
-  });
-  const payload = parsePayload(envelope);
-  assert.equal(payload.can_spawn_subagent_tool, true);
-});
-
-test('parsePayload still reads Claude stream array envelopes', () => {
-  const envelope = JSON.stringify([
-    { type: 'message', content: 'working' },
-    { type: 'result', result: JSON.stringify(E1_CLAIM_PAYLOAD) },
-  ]);
-  const payload = parsePayload(envelope);
-  assert.equal(payload.can_spawn_subagent_tool, true);
-  assert.deepEqual(payload.tool_names, ['spawn_subagent']);
-});
-
-test('isWorkflowToolAbsent accepts consistent absence', () => {
-  assert.equal(
-    isWorkflowToolAbsent({ has_workflow_tool: false, result: 'no_tool' }),
-    true,
-  );
-});
-
-test('isWorkflowToolAbsent rejects contradictory true and no_tool', () => {
-  assert.equal(
-    isWorkflowToolAbsent({ has_workflow_tool: true, result: 'no_tool' }),
-    false,
-  );
-});
-
-test('isWorkflowToolAbsent rejects contradictory false and has_tool', () => {
-  assert.equal(
-    isWorkflowToolAbsent({ has_workflow_tool: false, result: 'has_tool' }),
-    false,
-  );
-});
-
-test('isWorkflowToolAbsent rejects consistent presence', () => {
-  assert.equal(
-    isWorkflowToolAbsent({ has_workflow_tool: true, result: 'has_tool' }),
-    false,
-  );
-});
-
-test('isWorkflowToolAbsent rejects partial or missing fields', () => {
-  assert.equal(isWorkflowToolAbsent({ has_workflow_tool: false }), false);
-  assert.equal(isWorkflowToolAbsent({ result: 'no_tool' }), false);
-  assert.equal(isWorkflowToolAbsent(null), false);
-  assert.equal(isWorkflowToolAbsent({}), false);
-});