@codename_inc/spectre 5.2.2 → 5.3.0

package/plugins/spectre-codex/skills/{scope → spectre-scope}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "scope"
+name: "spectre-scope"
 description: "👻 | Interactively scope a feature or improvement, generating a complete Scope document with IN, OUT, and ANTI-SCOPE boundaries -- primary agent"
 user-invocable: true
 ---
@@ -30,7 +30,7 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
   - `branch_name=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo unknown)`
   - Look for: `docs/tasks/{branch_name}/concepts/scope.md`, `docs/tasks/{branch_name}/task_context.md`
   - **If** prior `scope.md` exists → read fully; treat this invocation as a re-scope. Surface what was already settled and ask only about what's new or changed.
-  - **If** captured project knowledge is available (via `apply`-style memory or session logs) → surface decisions/patterns/gotchas relevant to this area before asking the user.
+  - **If** captured project knowledge is available (via `spectre-apply`-style memory or session logs) → surface decisions/patterns/gotchas relevant to this area before asking the user.
 
 ## Step 2: Ground the Hypothesis (Fast)
 
@@ -41,9 +41,9 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
   - **One `grep` or `glob`** — when you need to verify a specific assumption ("does X already exist?")
 
   **Constraints**:
-  - **One call only.** This is grounding, not research. Tech research is `plan`'s job.
+  - **One call only.** This is grounding, not research. Tech research is `spectre-plan`'s job.
   - **Fast.** If the call would take more than a few seconds, skip it and ask the user instead.
-  - If you need more than one signal, that's a sign this should be a `kickoff` rather than a `scope`.
+  - If you need more than one signal, that's a sign this should be a `spectre-kickoff` rather than a `spectre-scope`.
 
 ## Step 3: Interactive Scope Exploration
 
@@ -51,7 +51,7 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
 
 - **Action** — ExploreScope: Collaborative dialogue focused on boundaries, user experience, and anti-scope.
 
-  **CRITICAL**: Focus on WHAT, not HOW. Defer all technical/implementation questions to `plan`. Only ask technical questions if the scope itself is inherently technical (e.g., "migrate database from X to Y").
+  **CRITICAL**: Focus on WHAT, not HOW. Defer all technical/implementation questions to `spectre-plan`. Only ask technical questions if the scope itself is inherently technical (e.g., "migrate database from X to Y").
 
   **PATTERN**: Lead with a grounded hypothesis (informed by Step 2's lookup) AND ask 5–8 questions across multiple dimensions. Mark each question as **(blocking)** or *(optional)* so the user can skim and skip.
 
@@ -82,7 +82,7 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
   - **Edge cases**: What happens when [unusual situation]?
   - **Success**: What makes you say "this shipped well"?
 
-  **DO NOT ask about**: implementation approach, technical trade-offs, architecture, or integration details — those belong in `plan`.
+  **DO NOT ask about**: implementation approach, technical trade-offs, architecture, or integration details — those belong in `spectre-plan`.
 
 - **Action** — IterateBoundaries: After user responds, refine boundaries and ask targeted follow-ups on gaps.
 
@@ -114,7 +114,7 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
   - For trade-off decisions, present options with concise pros/cons.
   - If more than 4 questions, ask in batches — most important first.
 
-  **CRITICAL**: Only ask about unresolved scope ambiguities. Technical questions belong in `plan`, not here.
+  **CRITICAL**: Only ask about unresolved scope ambiguities. Technical questions belong in `spectre-plan`, not here.
 
 ### Path B: File-Based Clarifications (no AskUserQuestion)
 
@@ -145,7 +145,7 @@ Collaborative workflow for structuring unstructured thoughts into clear scope bo
   7. **Constraints** — platform, perf, a11y, scale (user-provided only)
   8. **Decisions** — from clarifications + rationale
   9. **Risks** — UX, scope creep, open questions
-  10. **Next Steps** — `plan` or `create_tasks`, complexity S/M/L
+  10. **Next Steps** — `spectre-plan` or `spectre-create_tasks`, complexity S/M/L
 
   **Note on ANTI-SCOPE vs OUT**:
   - **OUT** = we're not building it (yet, or for this release).

package/plugins/spectre-codex/skills/{ship → spectre-ship}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "ship"
+name: "spectre-ship"
 description: "👻 | Autonomous end-to-end: brain dump -> scope -> TDD -> commit -> rebase -> PR"
 user-invocable: true
 ---
@@ -70,7 +70,7 @@ Take a brain dump and autonomously produce a reviewable PR. Zero confirmation ga
   {from research — relevant files and their roles}
   ```
 
-  Keep it \~20 lines. This is a lightweight scope, not full `scope`.
+  Keep it \~20 lines. This is a lightweight scope, not full `spectre-scope`.
 
 ## Step (4/8) - Create Tasks
 
@@ -98,7 +98,7 @@ Take a brain dump and autonomously produce a reviewable PR. Zero confirmation ga
 
 ## Step (6/8) - Sweep
 
-Inline sweep — same checklist as `sweep`, no subagents:
+Inline sweep — same checklist as `spectre-sweep`, no subagents:
 
 ### 6.1 Diff Sanity Check
 
@@ -171,7 +171,7 @@ Inline sweep — same checklist as `sweep`, no subagents:
   ## Test Plan
   {Bulleted checklist — what was tested, what to verify manually}
   
-  Shipped autonomously via `ship`
+  Shipped autonomously via `spectre-ship`
   ```
 
 - **Action** — OutputPRUrl: Display the PR URL as the final deliverable

package/plugins/spectre-codex/skills/{sweep → spectre-sweep}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "sweep"
+name: "spectre-sweep"
 description: "👻 | Light pass cleanup - clean, lint, test, commit"
 user-invocable: true
 ---

package/plugins/spectre-codex/skills/{tdd → spectre-tdd}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "tdd"
+name: "spectre-tdd"
 description: "Load this skill when executing TDD (Test-Driven Development) methodology. Use when implementing features via strict RED-GREEN-REFACTOR cycles, or when a prompt instructs execution via TDD."
 ---
 

package/plugins/spectre-codex/skills/{test → spectre-test}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "test"
+name: "spectre-test"
 description: "👻 | Risk-aware test coverage & commit - primary agent"
 user-invocable: true
 ---

package/plugins/spectre-codex/skills/{ux → spectre-ux}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "ux"
+name: "spectre-ux"
 description: "👻 | Define user flows, components, and UX behavior — generates the UX spec for a feature - primary agent"
 user-invocable: true
 ---
@@ -28,7 +28,7 @@ Transform product requirements into a definitive behavioral specification. Two s
    - `docs/tasks/{branch}/concepts/scope.md` — the canonical scope doc (preferred)
    - `docs/tasks/{branch}/specs/prd.md` — if a PRD was generated separately
    - `docs/tasks/{branch}/task_summary.md` — if present
-   - **If none exist** → ask the user for scope context (or recommend `scope` first) before proceeding.
+   - **If none exist** → ask the user for scope context (or recommend `spectre-scope` first) before proceeding.
 2. **Research patterns**: Dispatch `@patterns` to find existing screens/components similar to what we're building. Note conventions, reusable elements, and any design tokens.
 3. **Identify user segments**: List the user segments this feature serves — first-time vs returning, anonymous vs signed-in, free vs paid, role-based variants. UX often diverges across segments and missing this is a common cause of rework.
 4. **Identify journeys**: List user goals, entry points, and completion states.
@@ -102,11 +102,11 @@ Prompt:
 >
 > Written to `{path}`. Please review: Any behaviors wrong or missing? Edge cases not covered? Segment differences captured?
 >
-> **Want a prototype to validate visually before approving?** `prototype` will render this spec (high-fi, no synthesis) and flag assumptions where I had to fill in details — catches issues prose review misses. Reply `prototype` to run it now.
+> **Want a prototype to validate visually before approving?** `spectre-prototype` will render this spec (high-fi, no synthesis) and flag assumptions where I had to fill in details — catches issues prose review misses. Reply `prototype` to run it now.
 >
 > Otherwise, reply with feedback, or **"Approved"** to finalize.
 
-**Wait for approval, feedback, or prototype request.** If user replies `prototype`, invoke `prototype` (the post-ux mode auto-detects the complete ux.md). Once prototype completes and any spec updates from filled assumptions are applied, return here for final approval.
+**Wait for approval, feedback, or prototype request.** If user replies `prototype`, invoke `spectre-prototype` (the post-ux mode auto-detects the complete ux.md). Once prototype completes and any spec updates from filled assumptions are applied, return here for final approval.
 
 ## Step 5 — Handoff
 
@@ -116,6 +116,6 @@ Read `.spectre/next_steps_guide.md` and render Next Steps footer:
 
 ```
 Next Steps | Phase: Scope | Status: UX Complete
-Recommendation: {contextual next action — if no prototype was generated, suggest prototype to validate the spec visually before /plan}
-Options: prototype (validate spec visually), create_plan, create_tasks, tdd
+Recommendation: {contextual next action — if no prototype was generated, suggest spectre-prototype to validate the spec visually before /plan}
+Options: spectre-prototype (validate spec visually), spectre-create_plan, spectre-create_tasks, spectre-tdd
 ```

package/plugins/spectre-codex/skills/{validate → spectre-validate}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "validate"
+name: "spectre-validate"
 description: "👻 | Comprehensive post implementation requirement validation using subagents"
 user-invocable: true
 ---

package/src/config.test.js

@@ -131,5 +131,5 @@ test('buildSessionStartOutput keeps knowledge active when no handoff exists and
   assert.doesNotMatch(overrideContent, /spectre-session:start/);
   assert.match(overrideContent, /spectre-knowledge:start/);
   assert.match(overrideContent, /If ANY skill's triggers or description match your current task, you MUST load the skill FIRST/);
-  assert.match(overrideContent, /Capture via `Skill\(learn\)`/);
+  assert.match(overrideContent, /Capture via `Skill\(spectre-learn\)`/);
 });

package/src/install.test.js

@@ -34,26 +34,30 @@ test('project install writes workflow skills, agent config, and official Session
   delete process.env.CODEX_HOME;
 
   try {
+    fs.mkdirSync(path.join(projectDir, '.codex', 'skills', 'scope'), { recursive: true });
+    fs.writeFileSync(path.join(projectDir, '.codex', 'skills', 'scope', 'SKILL.md'), 'legacy bare scope skill\n');
+
     const { main } = await import('./main.js');
     await main(['install', 'codex', '--scope', 'project', '--project-dir', projectDir]);
 
     const codeHome = path.join(projectDir, '.codex');
-    const scopeSkillPath = path.join(codeHome, 'skills', 'scope', 'SKILL.md');
+    const scopeSkillPath = path.join(codeHome, 'skills', 'spectre-scope', 'SKILL.md');
     assert.ok(fs.existsSync(scopeSkillPath));
+    assert.ok(!fs.existsSync(path.join(codeHome, 'skills', 'scope')));
     const scopeSkill = fs.readFileSync(scopeSkillPath, 'utf8');
     assert.match(scopeSkill, /# scope: Interactive Feature Scoping/);
     assert.doesNotMatch(scopeSkill, /This is the Codex skill replacement for the deprecated custom prompt \/spectre:scope/);
-    assert.doesNotMatch(scopeSkill, /Skill\(spectre-scope\)/);
+    assert.doesNotMatch(scopeSkill, /Skill\(scope\)/);
 
-    const applySkillPath = path.join(codeHome, 'skills', 'apply', 'SKILL.md');
+    const applySkillPath = path.join(codeHome, 'skills', 'spectre-apply', 'SKILL.md');
     assert.ok(fs.existsSync(applySkillPath));
     assert.match(fs.readFileSync(applySkillPath, 'utf8'), /If ANY skill's triggers or description match your current task, you MUST load the skill FIRST/);
 
-    const learnSkillPath = path.join(codeHome, 'skills', 'learn', 'SKILL.md');
+    const learnSkillPath = path.join(codeHome, 'skills', 'spectre-learn', 'SKILL.md');
     assert.ok(fs.existsSync(learnSkillPath));
     assert.match(fs.readFileSync(learnSkillPath, 'utf8'), /### 13\. Register the Learning/);
     assert.match(fs.readFileSync(learnSkillPath, 'utf8'), /\.agents\/skills\/spectre-recall\/references\/registry\.toon/);
-    assert.ok(fs.existsSync(path.join(codeHome, 'skills', 'learn', 'references', 'recall-template.md')));
+    assert.ok(fs.existsSync(path.join(codeHome, 'skills', 'spectre-learn', 'references', 'recall-template.md')));
 
     const agentPath = path.join(codeHome, 'spectre', 'agents', 'dev.toml');
     assert.ok(fs.existsSync(agentPath));
@@ -335,7 +339,7 @@ test('project uninstall removes managed workflow skills, agent config, and proje
 
     const codeHome = path.join(projectDir, '.codex');
 
-    assert.ok(!fs.existsSync(path.join(codeHome, 'skills', 'scope')));
+    assert.ok(!fs.existsSync(path.join(codeHome, 'skills', 'spectre-scope')));
     assert.ok(!fs.existsSync(path.join(codeHome, 'spectre')));
 
     const config = fs.readFileSync(path.join(codeHome, 'config.toml'), 'utf8');

package/src/lib/constants.js

@@ -29,18 +29,18 @@ export function listSpectreAgents() {
 }
 
 export const SHARED_SKILLS = [
-  'apply',
-  'guide',
-  'learn',
-  'tdd'
+  'spectre-apply',
+  'spectre-guide',
+  'spectre-learn',
+  'spectre-tdd'
 ];
 
 export const WORKFLOW_PROBE_SKILLS = [
-  'scope',
-  'plan',
-  'execute',
-  'clean',
-  'test'
+  'spectre-scope',
+  'spectre-plan',
+  'spectre-execute',
+  'spectre-clean',
+  'spectre-test'
 ];
 
 export function repoMetadata() {

package/src/lib/install.js

@@ -88,6 +88,10 @@ function managedCodexSkillNames({ requireGenerated = false } = {}) {
   ])).sort();
 }
 
+function legacyBareSkillName(skillName) {
+  return skillName.startsWith('spectre-') ? skillName.slice('spectre-'.length) : null;
+}
+
 function replaceDirectory(sourceDir, targetDir) {
   if (!fs.existsSync(sourceDir)) {
     throw new Error(`Missing generated Codex asset directory: ${sourceDir}. Run npm run sync-codex first.`);
@@ -104,12 +108,34 @@ function removeLegacyPrefixedSkillDirs() {
     return;
   }
 
+  const managedNames = managedCodexSkillNames();
+
   for (const entry of fs.readdirSync(skillsRoot, { withFileTypes: true })) {
     if (!entry.isDirectory() || !entry.name.startsWith('spectre-')) {
       continue;
     }
     const bareName = entry.name.slice('spectre-'.length);
-    if (managedCodexSkillNames().includes(bareName)) {
+    if (managedNames.includes(bareName)) {
+      fs.rmSync(path.join(skillsRoot, entry.name), { recursive: true, force: true });
+    }
+  }
+}
+
+function removeLegacyBareSkillDirs() {
+  const skillsRoot = codexSkillsDir();
+  if (!fs.existsSync(skillsRoot)) {
+    return;
+  }
+
+  const legacyNames = new Set(managedCodexSkillNames().map(legacyBareSkillName).filter(Boolean));
+
+  for (const entry of fs.readdirSync(skillsRoot, { withFileTypes: true })) {
+    if (!entry.isDirectory() || !legacyNames.has(entry.name)) {
+      continue;
+    }
+
+    const skillPath = path.join(skillsRoot, entry.name, 'SKILL.md');
+    if (fs.existsSync(skillPath)) {
       fs.rmSync(path.join(skillsRoot, entry.name), { recursive: true, force: true });
     }
   }
@@ -121,6 +147,7 @@ function installGeneratedCodexSkills() {
   ensureDir(skillsRoot);
 
   removeLegacyPrefixedSkillDirs();
+  removeLegacyBareSkillDirs();
 
   for (const skillName of managedCodexSkillNames({ requireGenerated: true })) {
     const skillDir = path.join(skillsRoot, skillName);
@@ -250,6 +277,7 @@ export function uninstallCodex({ scope, projectDir }) {
   }
 
   removeLegacyPrefixedSkillDirs();
+  removeLegacyBareSkillDirs();
 
   for (const skillName of managedCodexSkillNames()) {
     const skillDir = path.join(codexSkillsDir(), skillName);

package/src/lib/knowledge.js

@@ -20,7 +20,9 @@ function rewriteProjectSkillPaths(content) {
 }
 
 function rewriteCodexCommandRefs(content) {
-  return content.replaceAll('/spectre:', '');
+  return content.replace(/\/spectre:([A-Za-z0-9_-]+)/g, (_match, skillName) => {
+    return skillName.startsWith('spectre-') ? skillName : `spectre-${skillName}`;
+  });
 }
 
 function markUserInvocable(content, value = true) {
@@ -70,7 +72,7 @@ function pluginSkillPath(skillName) {
 }
 
 function recallTemplatePath() {
-  return path.join(spectrePluginRoot(), 'skills', 'learn', 'references', 'recall-template.md');
+  return path.join(spectrePluginRoot(), 'skills', 'spectre-learn', 'references', 'recall-template.md');
 }
 
 function pluginSkillContent(skillName) {
@@ -78,11 +80,11 @@ function pluginSkillContent(skillName) {
 }
 
 export function codexSharedSkillContent(skillName) {
-  if (skillName === 'apply') {
+  if (skillName === 'spectre-apply') {
     return `${normalizeSkillMarkdown(rewriteCodexCommandRefs(rewriteProjectSkillPaths(pluginSkillContent(skillName))))}\n`;
   }
 
-  if (skillName === 'learn') {
+  if (skillName === 'spectre-learn') {
     return `${normalizeSkillMarkdown(markUserInvocable(rewriteCodexCommandRefs(codexPathConvention(codexLearnIntro(rewriteProjectSkillPaths(pluginSkillContent(skillName)))))))}\n`;
   }
 
@@ -142,7 +144,7 @@ export function ensureKnowledgeFiles(projectDir) {
 export function buildKnowledgeOverrideBody(projectDir) {
   ensureKnowledgeFiles(projectDir);
   const applyContent = stripFrontmatter(
-    rewriteCodexCommandRefs(rewriteProjectSkillPaths(pluginSkillContent('apply')))
+    rewriteCodexCommandRefs(rewriteProjectSkillPaths(pluginSkillContent('spectre-apply')))
   );
 
   return normalizeSkillMarkdown(applyContent);

package/src/pack.test.js

@@ -64,7 +64,7 @@ test('packed npm artifact installs Codex assets from generated tree', { concurre
     });
 
     const codexHome = path.join(projectDir, '.codex');
-    assert.ok(fs.existsSync(path.join(codexHome, 'skills', 'plan', 'SKILL.md')));
+    assert.ok(fs.existsSync(path.join(codexHome, 'skills', 'spectre-plan', 'SKILL.md')));
     assert.ok(fs.existsSync(path.join(codexHome, 'spectre', 'agents', 'dev.toml')));
     assert.ok(fs.existsSync(path.join(codexHome, 'spectre', 'hooks', 'scripts', 'load-knowledge.mjs')));
     assert.ok(!fs.existsSync(path.join(codexHome, 'spectre', 'hooks', 'session-start.mjs')));

package/plugins/spectre/skills/recall/SKILL.md

@@ -1,17 +0,0 @@
----
-name: recall
-description: "👻 | Search Project Knowledge"
-user-invocable: true
----
-
-# recall
-
-## Input Handling
-
-Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value.
-
-# /recall - Search Project Knowledge
-
-Load the `spectre-recall` skill and follow its instructions.
-
-**Search query**: $ARGUMENTS

package/plugins/spectre-codex/skills/recall/SKILL.md

@@ -1,17 +0,0 @@
----
-name: "recall"
-description: "👻 | Search Project Knowledge"
-user-invocable: true
----
-
-# recall
-
-## Input Handling
-
-Treat the current command arguments as this workflow's input. When invoked from a slash command, use the forwarded `$ARGUMENTS` value.
-
-# /recall - Search Project Knowledge
-
-Load the `spectre-recall` skill and follow its instructions.
-
-**Search query**: $ARGUMENTS