prizmkit 1.1.142 → 1.1.144

package/bundled/skills/prizmkit-test/references/independent-test-review.md

@@ -18,66 +18,62 @@ Main Agent builds and executes project-native tests
 → TEST_PASS | TEST_NEEDS_FIXES | TEST_BLOCKED
 ```
 
-Create at most one Reviewer for this invocation. Reuse the exact same Reviewer through native continuation. Never reuse a Reviewer from another lifecycle stage and never create a replacement with a summary to simulate continuation.
+Keep at most one Reviewer active for this invocation and permit at most one replacement. Prefer native continuation and never reuse a Reviewer from another lifecycle stage. A compliant replacement may continue the same shared response budget only with complete latest state, never only a conversation summary.
 
 ## Host Capability Gate
 
-The gate is all-or-nothing. Before creating a Reviewer, the host must prove this semantic execution contract:
+The gate is all-or-nothing. Before creating a Reviewer, inspect the current host's actual execution-unit configuration and prove this semantic contract without relying on platform identity or implementation-specific parameters:
 
 ```yaml
 execution_unit:
-  count: 1
-  access: read-only
-  mutation: unavailable
-  arbitrary_command_execution: unavailable
+  concurrency: at-most-one-active-reviewer
+  workspace_access: read-only-active-checkout
+  mutation: structurally-unavailable
+  command_execution: structurally-unavailable
+  network_access: structurally-unavailable
+  external_process_execution: structurally-unavailable
   downstream_execution: structurally-unavailable
-  context_continuation: same-unit-native-resume
-  workspace_observation: bounded-active-checkout-input
   model_configuration: inherit-current-session
+  scope_expansion: concrete-coupling-only
+  continuation: prefer-same-unit
+  replacement: compliant-replacement-allowed
 ```
 
 Rules:
 
 - Prompt instructions cannot satisfy a missing structural capability.
-- Do not branch on platform identity, tool name, execution-unit type name, adapter output, or an allowlist.
-- A general execution unit that merely promises not to mutate, execute commands, or delegate is ineligible while those capabilities remain available.
+- Do not branch on platform identity, provider, tool name, command name, execution-unit type name, adapter output, CLI parameter, or an allowlist.
+- The Reviewer cannot create, modify, delete, rename, stage, or commit files; execute shell, Git, tests, builds, network calls, or external processes; or create, invoke, resume, or coordinate downstream execution units.
+- A general execution unit that merely promises to stay read-only is ineligible while prohibited capabilities remain available.
 - The Reviewer inherits the current session's model configuration.
 - If any capability is missing or unproven, create no Reviewer and use Strict Downgrade.
 
-## Bounded Immutable Review Input
+## Stage-Specific Review Input
 
-Before every response, the Main Agent captures a complete input that remains immutable for that response:
+Resolve exact requirement identity from workflow state or explicit handoff on every response:
 
 ```text
-test-review-input
-├── manifest
-│   ├── response number and input identity
-│   ├── exact changed production and test paths
-│   ├── relevant unchanged path inventory
-│   └── consistency markers
-├── change context
-│   ├── requirement and acceptance criteria
-│   ├── current production change
-│   └── applicable project rules
-├── coverage context
-│   ├── affected business module
-│   ├── observable behaviors
-│   ├── risk and boundary assessment
-│   └── Regression Ring
-├── test context
-│   ├── existing, added, and modified tests
-│   ├── fixtures, mocks, and contracts
-│   ├── selected test layers
-│   └── native execution results
-└── targeted supporting context
-    ├── relevant callers and consumers
-    ├── shared schemas and contracts
-    └── necessary public official contract excerpts
+artifact_dir: [EXACT_ARTIFACT_DIR]
+spec_path: [EXACT_SPEC_PATH]
+plan_path: [EXACT_PLAN_PATH]
+checkout_root: [ACTIVE_CHECKOUT_ROOT]
 ```
 
-The Reviewer does not run Git, tests, builds, network calls, or broad repository discovery. The Main Agent captures authoritative current state. Do not include secrets, credentials, production data, or unrelated private repository content.
+These paths remain authoritative even when ignored by Git. Never ask the Reviewer to discover a latest artifact or guess among multiple `spec.md` and `plan.md` files.
 
-Before ordinary review, the Reviewer verifies that manifest and content agree. Missing paths, unexplained changed files, stale content, or mixed-response input produces `REVIEW_BLOCKED`, never partial success.
+The Main Agent supplies:
+
+- original requirement and confirmed clarifications;
+- exact artifact, spec, and plan paths plus current contents;
+- complete current production-and-test change;
+- affected business module, observable behaviors, applicable risks, and Regression Ring;
+- existing, added, and modified tests, fixtures, mocks, schemas, contracts, and selected layers;
+- native test commands and results executed by Main Agent;
+- test-stage repairs;
+- response number and total budget;
+- prior adjudication and actual corrections on continuation or replacement.
+
+The Reviewer may use structurally read-only checkout access to inspect production code, tests, fixtures, schemas, callers, consumers, and contracts only through concrete coupling evidence. It cannot run Git, tests, builds, network calls, or external processes and must not perform an unconditional repository-wide scan. Do not include secrets, credentials, production data, or unrelated private content. Missing or inconsistent required input produces `REVIEW_BLOCKED`, never partial success.
 
 ## Initial Reviewer Prompt
 
@@ -91,12 +87,14 @@ Objectively determine whether the complete current project-native tests credibly
 
 Response:
 This is response [RESPONSE_NUMBER] of a maximum five responses.
-Review-input identity: [INPUT_ID]
-Manifest: [MANIFEST]
-Change context: [CHANGE_CONTEXT]
+Artifact directory: [ARTIFACT_DIR]
+Specification path and content: [SPEC_PATH_AND_CONTENT]
+Plan path and content: [PLAN_PATH_AND_CONTENT]
+Checkout root: [CHECKOUT_ROOT]
+Requirement and clarifications: [REQUIREMENT_CONTEXT]
+Current production-and-test change: [CURRENT_CHANGE]
 Coverage context: [COVERAGE_CONTEXT]
-Test context: [TEST_CONTEXT]
-Targeted supporting context: [SUPPORTING_CONTEXT]
+Test context and Main-Agent execution results: [TEST_CONTEXT]
 
 Execution boundaries:
 - Complete this review personally.
@@ -104,9 +102,9 @@ Execution boundaries:
 - Do not ask the Main Agent to create a helper.
 - Do not re-enter orchestration, delegation, another review workflow, or an equivalent process.
 - Do not modify, create, delete, rename, stage, commit, or otherwise mutate files.
-- Do not execute commands, tests, builds, network calls, or any operation that can change state.
-- Read only the bounded review input and explicitly represented targeted supporting material.
-- Do not perform broad repository discovery or a full repository scan.
+- Do not execute shell, Git, tests, builds, network calls, external processes, or any operation that can change state.
+- Use read-only checkout access only for concrete module, caller, consumer, schema, type, configuration, fixture, test, or contract coupling.
+- Do not perform unconditional repository discovery or a full repository scan.
 - Report only corrections supported by a concrete target and evidence.
 - Do not invent an issue merely to return feedback.
 - Return REVIEW_BLOCKED rather than delegate or provide an incomplete success result.
@@ -134,19 +132,22 @@ Return exactly one result using the Reviewer Output Protocol.
 
 ## Resume Prompt
 
-Resume the exact same Reviewer. Do not create a new Reviewer with this prompt.
+Prefer native continuation of the same Reviewer. If unavailable, use this complete prompt for one compliant replacement under the replacement rules below.
 
 ```text
 Continue as the same independent Test Reviewer.
 
 Response:
 This is response [RESPONSE_NUMBER] of a maximum five responses.
-New review-input identity: [INPUT_ID]
-New manifest: [MANIFEST]
-Current change context: [CHANGE_CONTEXT]
+Continuation mode: [NATIVE_OR_REPLACEMENT]
+Artifact directory: [ARTIFACT_DIR]
+Specification path and content: [SPEC_PATH_AND_CONTENT]
+Plan path and content: [PLAN_PATH_AND_CONTENT]
+Checkout root: [CHECKOUT_ROOT]
+Requirement and clarifications: [REQUIREMENT_CONTEXT]
+Current production-and-test change: [CURRENT_CHANGE]
 Current coverage context: [COVERAGE_CONTEXT]
-Current test context: [TEST_CONTEXT]
-Current supporting context: [SUPPORTING_CONTEXT]
+Current test context and Main-Agent execution results: [TEST_CONTEXT]
 Previously accepted corrections: [ACCEPTED_CORRECTIONS_OR_NONE]
 Repairs actually made: [REPAIRS_OR_NONE]
 Main-Agent native verification: [VERIFICATION]
@@ -233,28 +234,25 @@ Independent review converges when:
 4. Validate the response against the output protocol and record it in the report.
 5. Adjudicate every correction and record accepted, rejected, or unresolved with evidence.
 6. For accepted corrections, the Main Agent repairs the current workspace, executes focused and required regressions, then performs a complete Main-Agent review round over the new state within its ten-round budget.
-7. If responses remain, capture the complete fresh input and natively resume the exact same Reviewer. Never create a replacement.
-8. If response five contains an accepted correction, do not repair and claim pass without independent recheck. Return `TEST_NEEDS_FIXES` with the known correction.
-9. If response five contains an unresolved correction or `REVIEW_BLOCKED` that cannot be corrected safely, return `TEST_BLOCKED`.
-10. Stop sending messages when the review converges, reaches its limit, or becomes blocked. Explicitly terminate the unit only when the host safely supports it.
+7. If responses remain, prepare the complete latest Test input and prefer native continuation. If unavailable or failed and no replacement has been used in this stage, create one compliant replacement only after the prior Reviewer is no longer active; reapply the full gate and continue with the next response number.
+8. A replacement receives complete current state and all prior adjudication, never only a conversation summary. Replacement does not reset the five-response budget. At most one replacement may be created in the stage, and only one Reviewer may be active.
+9. If response five contains an accepted correction, do not repair and claim pass without independent recheck. Return `TEST_NEEDS_FIXES` with the known correction.
+10. If response five contains an unresolved correction or `REVIEW_BLOCKED` that cannot be corrected safely, return `TEST_BLOCKED`.
+11. Stop sending messages when the review converges, reaches its limit, or becomes blocked. Explicitly terminate the unit only when the host safely supports it.
 
 ## Strict Downgrade
 
-Use Strict Downgrade when:
-
-- required capability is unavailable or unproven before creation;
-- creation fails before a valid response;
-- a required structural capability disappears;
-- exact native resume fails after mutation.
+Use Strict Downgrade when a required capability is unavailable or unproven, creation fails before a valid response, prohibited capability appears, the prior Reviewer may still be active, or no compliant continuation/replacement can be established.
 
 Behavior:
 
-1. Never create a weaker or replacement Reviewer.
-2. Never create a fresh Reviewer with a summary; summary context is not native continuation.
-3. Before creation or before any valid response, record the downgrade and preserve the converged mandatory Main-Agent review.
-4. When resume fails after mutation, the old independent result no longer describes the final state. Rerun mandatory Main-Agent review over the mutation within its remaining budget, record the downgrade, and set `final_state_rechecked=false` for independent review.
-5. A semantic `REVIEW_BLOCKED` caused by incomplete or inconsistent required input is not silently downgraded. Correct the input and resume the same Reviewer within budget, or return `TEST_BLOCKED`.
-6. Strict Downgrade is visible reduced assurance, not a new testing result and not permission to weaken Main-Agent review or native test execution.
+1. Never create a weaker Reviewer whose prohibited capabilities remain available.
+2. Prefer native continuation, but permit a fresh compliant replacement with complete latest input and prior adjudication; a summary alone is insufficient.
+3. Before creation or before any valid response, record downgrade and preserve the converged mandatory Main-Agent review.
+4. Creation failure without a response does not consume response budget; a produced malformed response follows the existing response-budget rule.
+5. When continuation and compliant replacement both fail after mutation, rerun mandatory Main-Agent review over the mutation within remaining budget, record downgrade, and set `final_state_rechecked=false`.
+6. A semantic `REVIEW_BLOCKED` caused by incomplete required input is not silently downgraded. Correct input within remaining shared budget using native continuation or compliant replacement, or return `TEST_BLOCKED`.
+7. Strict Downgrade is visible reduced assurance, not a new testing result and not permission to weaken Main-Agent review or native execution.
 
 ## Report Recording
 
@@ -264,6 +262,7 @@ Record:
 - each response number `1..5`, input identity, result, and correction count;
 - every Main-Agent adjudication and its evidence;
 - actual repair and native verification;
-- whether the exact final state was independently rechecked.
+- whether the exact final state was independently rechecked;
+- capability basis, continuation mode (`native`, `replacement`, `mixed`, or `not-applicable`), and replacement count.
 
 The report remains the human-readable test artifact. Do not create a separate Reviewer state machine or evidence package.

package/bundled/skills/prizmkit-test/references/test-report-template.md

@@ -78,8 +78,12 @@ Coverage metrics, when available: <diagnostic values or not collected>. Percenta
 ## Independent Test Review
 
 - Status: completed / downgraded / not_applicable
+- Capability Gate: <ENABLED | DOWNGRADED | NOT_APPLICABLE>
+- Capability Basis: <platform-neutral structural evidence or unavailable>
+- Downgrade Reason: <reason or none>
 - Responses: <0..5>
-- Capability gate or downgrade reason: <reason or none>
+- Continuation Mode: <native | replacement | mixed | not-applicable>
+- Reviewer Replacements: <0..1>
 - Corrections and Main-Agent adjudication: <summary or none>
 - Exact final state independently rechecked: yes / no
 

package/bundled/templates/hooks/commit-intent-status.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+"""Report whether staged source changes include Prizm documentation updates."""
+
+from __future__ import annotations
+
+import subprocess
+
+SOURCE_EXTENSIONS = (".ts", ".tsx", ".js", ".jsx", ".py", ".go", ".rs", ".java")
+PRIZM_DOCS_PREFIX = ".prizmkit/prizm-docs/"
+
+
+def staged_files() -> list[str]:
+    result = subprocess.run(
+        ["git", "diff", "--cached", "--name-only"],
+        text=True,
+        encoding="utf-8",
+        errors="replace",
+        stdout=subprocess.PIPE,
+        stderr=subprocess.DEVNULL,
+        check=False,
+    )
+    if result.returncode != 0:
+        return []
+    return [path for path in result.stdout.splitlines() if path.strip()]
+
+
+def main() -> int:
+    files = staged_files()
+    source_files = [path for path in files if path.endswith(SOURCE_EXTENSIONS)]
+    if not source_files:
+        return 0
+
+    prizm_docs = [path for path in files if path.startswith(PRIZM_DOCS_PREFIX)]
+    if prizm_docs:
+        print(
+            f"PRIZMKIT_DOC_STATUS: {len(source_files)} source file(s) staged | "
+            f".prizmkit/prizm-docs/ updated ({len(prizm_docs)} file(s))",
+            end="",
+        )
+    else:
+        print(
+            f"PRIZMKIT_DOC_STATUS: {len(source_files)} source file(s) staged | "
+            ".prizmkit/prizm-docs/ NOT UPDATED — update if this is a feature change",
+            end="",
+        )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/bundled/templates/hooks/commit-intent.json

@@ -6,7 +6,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "python3 -c \"import subprocess,sys; r=subprocess.run(['git','diff','--cached','--name-only'],text=True,encoding='utf-8',errors='replace',stdout=subprocess.PIPE,stderr=subprocess.DEVNULL); files=[p for p in r.stdout.splitlines() if p.strip()] if r.returncode==0 else []; src=[p for p in files if p.endswith(('.ts','.tsx','.js','.jsx','.py','.go','.rs','.java'))]; prizm=[p for p in files if p.startswith('.prizmkit/prizm-docs/')]; print(f'PRIZMKIT_DOC_STATUS: {len(src)} source file(s) staged | .prizmkit/prizm-docs/ updated ({len(prizm)} file(s))' if src and prizm else (f'PRIZMKIT_DOC_STATUS: {len(src)} source file(s) staged | .prizmkit/prizm-docs/ NOT UPDATED — update if this is a feature change' if src else ''), end='')\""
+            "command": "python3 .prizmkit/scripts/commit-intent-status.py"
           }
         ]
       }
@@ -17,7 +17,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "python3 -c \"import os,re,subprocess,sys; data=os.environ.get('CLAUDE_TOOL_INPUT') or os.environ.get('CODEBUDDY_TOOL_INPUT') or ''; script='.prizmkit/scripts/diff-prizm-docs.py'; should=bool(re.search(r'git\\s+(commit|merge|rebase)', data)); res=subprocess.run([sys.executable, script],text=True,encoding='utf-8',errors='replace',stdout=subprocess.PIPE,stderr=subprocess.DEVNULL) if should and os.path.isfile(script) else None; drift=(res.stdout.strip() if res else ''); print('PRIZMKIT_DRIFT_DETECTED: prizm-docs structural differences found:\\n'+drift+'\\nPlease update affected .prizmkit/prizm-docs/ files.') if drift else None\""
+            "command": "python3 .prizmkit/scripts/post-command-prizm-drift.py"
           }
         ]
       }

package/bundled/templates/hooks/post-command-prizm-drift.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+"""Report Prizm documentation drift after relevant Git commands."""
+
+from __future__ import annotations
+
+import os
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+DRIFT_SCRIPT = Path(".prizmkit/scripts/diff-prizm-docs.py")
+RELEVANT_GIT_COMMAND = re.compile(r"git\s+(commit|merge|rebase)")
+
+
+def tool_input() -> str:
+    return os.environ.get("CLAUDE_TOOL_INPUT") or os.environ.get("CODEBUDDY_TOOL_INPUT") or ""
+
+
+def main() -> int:
+    if not RELEVANT_GIT_COMMAND.search(tool_input()) or not DRIFT_SCRIPT.is_file():
+        return 0
+
+    result = subprocess.run(
+        [sys.executable, str(DRIFT_SCRIPT)],
+        text=True,
+        encoding="utf-8",
+        errors="replace",
+        stdout=subprocess.PIPE,
+        stderr=subprocess.DEVNULL,
+        check=False,
+    )
+    drift = result.stdout.strip()
+    if drift:
+        print(
+            "PRIZMKIT_DRIFT_DETECTED: prizm-docs structural differences found:\n"
+            f"{drift}\n"
+            "Please update affected .prizmkit/prizm-docs/ files."
+        )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.142",
+  "version": "1.1.144",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {

package/src/ai-cli-launch.js

@@ -1,4 +1,4 @@
-const BUILT_IN_AI_CLI_NAMES = new Set(['claude', 'cbc', 'codebuddy', 'codex']);
+const BUILT_IN_AI_CLI_NAMES = new Set(['claude', 'cbc', 'codebuddy', 'codex', 'pi']);
 
 function asText(value) {
   return typeof value === 'string' ? value : '';

package/src/clean.js

@@ -252,6 +252,10 @@ export async function runClean(directory, options = {}) {
   const codexSkillsDir = path.join(projectRoot, '.agents', 'skills');
   results.push(...await removeKnownEntries(codexSkillsDir, allSkillNames, dryRun));
 
+  // .pi/skills/ — Pi project skills
+  const piSkillsDir = path.join(projectRoot, '.pi', 'skills');
+  results.push(...await removeKnownEntries(piSkillsDir, allSkillNames, dryRun));
+
   // .claude/agents/ — retired PrizmKit named-agent files
   const claudeAgentsDir = path.join(projectRoot, '.claude', 'agents');
   results.push(...await removeKnownEntries(claudeAgentsDir, agentFiles, dryRun));
@@ -280,13 +284,18 @@ export async function runClean(directory, options = {}) {
   const legacyCodexRulesDir = path.join(projectRoot, '.codex', 'rules');
   results.push(...await removeKnownEntries(legacyCodexRulesDir, ruleFileNames.map(n => `${n}.md`), dryRun));
 
-  for (const platform of ['codebuddy', 'claude', 'codex']) {
+  const piRulesDir = path.join(projectRoot, '.pi', 'rules');
+  results.push(...await removeKnownEntries(piRulesDir, ruleFileNames.map(n => `${n}.md`), dryRun));
+
+  for (const platform of ['codebuddy', 'claude', 'codex', 'pi']) {
     const memoryFile = projectMemoryFile(platform);
     const privateMemoryFile = privateProjectMemoryFile(platform);
-    if (!memoryFile || !privateMemoryFile) continue;
-    results.push(await cleanProjectMemoryImport(projectRoot, memoryFile, privateMemoryFile, dryRun));
+    if (!privateMemoryFile) continue;
+    if (memoryFile) {
+      results.push(await cleanProjectMemoryImport(projectRoot, memoryFile, privateMemoryFile, dryRun));
+      results.push(await cleanMarkedProjectMemory(projectRoot, memoryFile, dryRun));
+    }
     results.push(await cleanMarkedProjectMemory(projectRoot, privateMemoryFile, dryRun));
-    results.push(await cleanMarkedProjectMemory(projectRoot, memoryFile, dryRun));
   }
 
   // ── .gitignore cleanup ────────────────────────────────────────────────────

package/src/config.js

@@ -99,9 +99,11 @@ async function detectInstalledPlatforms(projectRoot) {
   const hasClaude = await hasPlatformFiles(path.join(projectRoot, '.claude', 'commands'));
   const hasCodeBuddy = await hasPlatformFiles(path.join(projectRoot, '.codebuddy', 'skills'));
   const hasCodex = await hasPlatformFiles(path.join(projectRoot, '.agents', 'skills'));
+  const hasPi = await hasPlatformFiles(path.join(projectRoot, '.pi', 'skills'));
+  const detected = [hasClaude && 'claude', hasCodeBuddy && 'codebuddy', hasCodex && 'codex', hasPi && 'pi'].filter(Boolean);
 
-  if (hasClaude && hasCodeBuddy && hasCodex) return 'all';
-  if (hasClaude && hasCodeBuddy) return 'both';
+  if (detected.length > 1) return detected.length === 2 && hasClaude && hasCodeBuddy ? 'both' : 'all';
+  if (hasPi) return 'pi';
   if (hasCodex) return 'codex';
   if (hasCodeBuddy) return 'codebuddy';
   if (hasClaude) return 'claude';
@@ -121,18 +123,25 @@ function logManagedMemoryWarnings(mainFile, warnings) {
 async function removeProjectMemoryArtifacts(platform, projectRoot, dryRun) {
   const mainFile = projectMemoryFile(platform);
   const privateFile = privateProjectMemoryFile(platform);
-  if (!mainFile || !privateFile) return;
+  if (!privateFile) return;
 
   const privatePath = path.join(projectRoot, privateFile);
   if (await fs.pathExists(privatePath)) {
+    const currentPrivate = await fs.readFile(privatePath, 'utf-8');
+    const normalizedPrivate = normalizeMainProjectMemoryContent(currentPrivate, null);
+    const remainingPrivate = normalizedPrivate.content.trim();
     if (dryRun) {
-      console.log(chalk.gray(`      [dry-run] remove ${privateFile}`));
+      console.log(chalk.gray(`      [dry-run] update ${privateFile} (remove PrizmKit block)`));
+    } else if (remainingPrivate) {
+      await fs.writeFile(privatePath, `${remainingPrivate}\n`, 'utf-8');
+      console.log(chalk.green(`      ✓ updated ${privateFile} (removed PrizmKit block)`));
     } else {
       await fs.remove(privatePath);
       console.log(chalk.red(`      ✗ removed ${privateFile}`));
     }
   }
 
+  if (!mainFile) return;
   const mainPath = path.join(projectRoot, mainFile);
   if (!await fs.pathExists(mainPath)) return;
 
@@ -252,10 +261,21 @@ async function removePlatformFiles(platform, projectRoot, manifest, dryRun) {
   } else {
     const settingsFile = platform === 'claude'
       ? path.join(projectRoot, '.claude', 'settings.json')
-      : path.join(projectRoot, '.codebuddy', 'settings.json');
+      : platform === 'pi'
+        ? path.join(projectRoot, '.pi', 'settings.json')
+        : path.join(projectRoot, '.codebuddy', 'settings.json');
     if (await fs.pathExists(settingsFile)) {
       if (dryRun) {
         console.log(chalk.gray(`      [dry-run] remove ${path.relative(projectRoot, settingsFile)}`));
+      } else if (platform === 'pi') {
+        let settings = {};
+        try { settings = await fs.readJSON(settingsFile); } catch { settings = null; }
+        if (settings && !Array.isArray(settings) && typeof settings === 'object') {
+          delete settings.enableSkillCommands;
+          if (Object.keys(settings).length) await fs.writeJSON(settingsFile, settings, { spaces: 2 });
+          else await fs.remove(settingsFile);
+          console.log(chalk.green('      ✓ removed PrizmKit Pi setting'));
+        }
       } else {
         await fs.remove(settingsFile);
         console.log(chalk.red(`      ✗ removed ${path.relative(projectRoot, settingsFile)}`));
@@ -353,6 +373,13 @@ async function removePlatformFiles(platform, projectRoot, manifest, dryRun) {
         }
       }
     }
+  } else if (platform === 'pi') {
+    for (const relativeDir of ['.pi/skills', '.pi/rules', '.pi']) {
+      const dir = path.join(projectRoot, relativeDir);
+      if (await fs.pathExists(dir) && !dryRun && (await fs.readdir(dir)).length === 0) {
+        await fs.remove(dir);
+      }
+    }
   }
 }
 

package/src/detect-platform.js

@@ -9,7 +9,7 @@ import os from 'os';
 /**
  * 允许检测的命令白名单（仅用于 which 检测）
  */
-const ALLOWED_COMMANDS = ['cbc', 'claude', 'codex'];
+const ALLOWED_COMMANDS = ['cbc', 'claude', 'codex', 'pi'];
 
 /**
  * 检查命令是否存在于 PATH 中
@@ -33,30 +33,34 @@ function commandExists(cmd) {
  * 注意：platform 控制目录结构（.codebuddy/ 或 .claude/），
  *       suggestedCli 是实际运行的可执行命令，二者相互独立。
  *
- * @returns {{ cbc: boolean, claude: boolean, codex: boolean, suggested: string, suggestedCli: string }}
+ * @returns {{ cbc: boolean, claude: boolean, codex: boolean, pi: boolean, suggested: string, suggestedCli: string }}
  */
 export function detectPlatform() {
   const cbc = commandExists('cbc');
   const claude = commandExists('claude');
   const codex = commandExists('codex');
+  const pi = commandExists('pi');
 
-  // platform 建议：基于目录结构
+  // Preserve historical recommendations when Pi is absent.
   let suggested = 'codebuddy';
-  if (cbc && claude && codex) {
+  if (pi) {
+    suggested = (cbc || claude || codex) ? 'all' : 'pi';
+  } else if (cbc && claude && codex) {
     suggested = 'all';
   } else if (codex && !cbc && !claude) {
     suggested = 'codex';
-  } else if ((claude) && !cbc) {
+  } else if (claude && !cbc) {
     suggested = 'claude';
   } else if (cbc && !claude) {
     suggested = 'codebuddy';
   }
 
-  // CLI 命令建议：优先 cbc，其次 claude，再次 codex
+  // Preserve historical precedence and use Pi when it is the first available CLI.
   let suggestedCli = '';
   if (cbc) suggestedCli = 'cbc';
   else if (claude) suggestedCli = 'claude';
   else if (codex) suggestedCli = 'codex';
+  else if (pi) suggestedCli = 'pi';
 
-  return { cbc, claude, codex, suggested, suggestedCli };
+  return { cbc, claude, codex, pi, suggested, suggestedCli };
 }

package/src/index.js

@@ -52,6 +52,7 @@ export async function runScaffold(directory, options) {
     detected.cbc ? chalk.green('cbc ✓') : chalk.gray('cbc ✗'),
     detected.claude ? chalk.green('claude ✓') : chalk.gray('claude ✗'),
     detected.codex ? chalk.green('codex ✓') : chalk.gray('codex ✗'),
+    detected.pi ? chalk.green('pi ✓') : chalk.gray('pi ✗'),
   ].join('  ');
   console.log(`  检测到的 CLI 工具:  ${cliStatus}`);
   console.log(`  目标目录:          ${projectRoot}`);
@@ -108,6 +109,10 @@ export async function runScaffold(directory, options) {
           name: `Codex (AGENTS.md + .agents/skills + .codex/)${detected.codex ? chalk.green(' ← 已检测到 codex') : ''}`,
           value: 'codex',
         },
+        {
+          name: `Pi (.pi/skills + .pi/APPEND_SYSTEM.md)${detected.pi ? chalk.green(' ← 已检测到 pi') : ''}`,
+          value: 'pi',
+        },
         {
           name: '同时安装全部平台',
           value: 'all',

package/src/platforms.js

@@ -1,6 +1,6 @@
 import { isBuiltInAiCli } from './ai-cli-launch.js';
 
-export const PLATFORM_IDS = ['codebuddy', 'claude', 'codex'];
+export const PLATFORM_IDS = ['codebuddy', 'claude', 'codex', 'pi'];
 export const PLATFORM_GROUPS = {
   all: PLATFORM_IDS,
 };
@@ -23,6 +23,7 @@ export function platformFromAiCli(aiCli) {
   const name = token.split(/[\\/]/).pop()?.toLowerCase() || '';
   if (name === 'claude') return 'claude';
   if (name === 'codex') return 'codex';
+  if (name === 'pi') return 'pi';
   if (name === 'cbc' || name === 'codebuddy') return 'codebuddy';
   return null;
 }
@@ -48,10 +49,11 @@ export function isKnownPlatform(platform) {
 
 export function platformLabel(platform) {
   if (platform === 'both') return 'legacy codebuddy/claude group';
-  if (platform === 'all') return 'All platforms (CodeBuddy, Claude Code, Codex)';
+  if (platform === 'all') return 'All platforms (CodeBuddy, Claude Code, Codex, Pi)';
   if (platform === 'codebuddy') return 'CodeBuddy';
   if (platform === 'claude') return 'Claude Code';
   if (platform === 'codex') return 'Codex';
+  if (platform === 'pi') return 'Pi';
   return platform;
 }
 
@@ -63,6 +65,7 @@ export function projectMemoryFile(platform) {
 }
 
 export function privateProjectMemoryFile(platform) {
+  if (platform === 'pi') return '.pi/APPEND_SYSTEM.md';
   const mainFile = projectMemoryFile(platform);
   if (!mainFile) return null;
   return mainFile.replace(/\.md$/i, '.private.md');
@@ -80,5 +83,6 @@ export function defaultCliForPlatform(platform) {
   if (platform === 'claude') return 'claude';
   if (platform === 'codebuddy') return 'cbc';
   if (platform === 'codex') return 'codex';
+  if (platform === 'pi') return 'pi';
   return '';
 }