@maxiaochao/pi-toolkit 0.1.3 → 0.1.4

package/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 2026-08-18 - v0.1.4
+
+- tbd
+
 ## 2026-08-18 - v0.1.3
 
 - tbd

package/global/AGENTS.md

@@ -0,0 +1,91 @@
+# AGENTS.md
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" -> "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" -> "Write a test that reproduces it, then make it pass"
+- "Refactor X" -> "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+1. [Step] -> verify: [check]
+2. [Step] -> verify: [check]
+3. [Step] -> verify: [check]
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+## 5. Read Before You Write
+
+**Understand adjacent code before changing it. "Looks orthogonal" is a dangerous assumption.**
+
+Before adding code to any file:
+- Read the file's exports and public API.
+- Read the immediate callers of the function you're modifying.
+- Check shared utilities in the same module.
+- If you're unsure why code is structured a certain way, ask before writing.
+
+## 6. Checkpoint Long-Running Work
+
+**Multi-step work needs checkpoints. Don't keep going from a state you can't describe.**
+
+After each significant step:
+- Summarize what was done.
+- State what was verified.
+- State what remains.
+- If you can't describe the current state back, stop and restate instead of continuing.
+
+## 7. Fail Visibly, Not Silently
+
+**Silent skips are failures. Surface uncertainty instead of hiding it.**
+
+- "Completed" is wrong if anything was silently skipped.
+- "Tests pass" is wrong if any test was skipped.
+- Default to surfacing uncertainty. When in doubt, over-communicate what you're unsure about.
+
+---
+
+**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@maxiaochao/pi-toolkit",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "Personal pi coding agent toolkit: /todos extension + /cache_export interactive cache dashboard.",
   "type": "module",
   "keywords": [
@@ -10,7 +10,9 @@
   "files": [
     "extensions",
     "README.md",
-    "CHANGELOG.md"
+    "CHANGELOG.md",
+    "global/AGENTS.md",
+    "scripts/install-agents.mjs"
   ],
   "repository": {
     "type": "git",
@@ -30,7 +32,8 @@
   },
   "scripts": {
     "test": "cd extensions/cache-export && node --experimental-strip-types tests/run-tests.mjs",
-    "load-test": "pi -e ./extensions/todo.ts && pi -e ./extensions/cache-export/index.ts"
+    "load-test": "pi -ne -e ./extensions/todo.ts && pi -ne -e ./extensions/cache-export/index.ts",
+    "postinstall": "node scripts/install-agents.mjs"
   },
   "publishConfig": {
     "access": "public"

package/scripts/install-agents.mjs

@@ -0,0 +1,15 @@
+// postinstall hook: sync the bundled global AGENTS.md to ~/.pi/agent/AGENTS.md
+// (pi's native global context file). Idempotent: writes only when different.
+import { readFileSync, writeFileSync, mkdirSync, existsSync } from "node:fs";
+import { homedir } from "node:os";
+import { dirname, join } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const bundled = readFileSync(join(dirname(fileURLToPath(import.meta.url)), "..", "global", "AGENTS.md"), "utf8");
+const target = join(homedir(), ".pi", "agent", "AGENTS.md");
+
+if (!existsSync(target) || readFileSync(target, "utf8") !== bundled) {
+  mkdirSync(dirname(target), { recursive: true });
+  writeFileSync(target, bundled, "utf8");
+  console.log("[pi-toolkit] global AGENTS.md synced ->", target);
+}