maxsimcli 3.3.1 → 3.5.0

package/README.md

@@ -8,8 +8,13 @@
 
 [![npm version](https://img.shields.io/npm/v/maxsimcli?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/maxsimcli)
 [![npm downloads](https://img.shields.io/npm/dm/maxsimcli?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/maxsimcli)
-[![GitHub stars](https://img.shields.io/github/stars/maystudios/maxsim?style=for-the-badge&logo=github&color=181717)](https://github.com/maystudios/maxsim)
-[![License](https://img.shields.io/badge/license-MIT-blue?style=for-the-badge)](LICENSE)
+[![GitHub stars](https://img.shields.io/github/stars/maystudios/maxsim?style=for-the-badge&logo=github&logoColor=white&color=24292e)](https://github.com/maystudios/maxsim)
+[![License](https://img.shields.io/badge/license-MIT-22c55e?style=for-the-badge)](LICENSE)
+
+<br>
+
+[![Website](https://img.shields.io/badge/Website-maxsimcli.dev-3b82f6?style=for-the-badge&logo=googlechrome&logoColor=white)](https://maxsimcli.dev/)
+[![Docs](https://img.shields.io/badge/Docs-maxsimcli.dev%2Fdocs-6366f1?style=for-the-badge&logo=readthedocs&logoColor=white)](https://maxsimcli.dev/docs)
 
 <br>
 

package/dist/assets/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [3.5.0](https://github.com/maystudios/maxsim/compare/v3.4.0...v3.5.0) (2026-02-26)
+
+
+### Features
+
+* **website:** comprehensive SEO overhaul with meta tags, sitemap, and structured data ([33db639](https://github.com/maystudios/maxsim/commit/33db6392345312f84a2d89a355a64d7d00335612))
+
+# [3.4.0](https://github.com/maystudios/maxsim/compare/v3.3.1...v3.4.0) (2026-02-26)
+
+
+### Features
+
+* **agents:** add self-improvement loop to MAXSIM agents ([48e12c3](https://github.com/maystudios/maxsim/commit/48e12c36a56013a880ca31524f47250aedcbb4bc))
+
 ## [3.3.1](https://github.com/maystudios/maxsim/compare/v3.3.0...v3.3.1) (2026-02-26)
 
 

package/dist/assets/templates/agents/maxsim-executor.md

@@ -21,6 +21,8 @@ Before executing, discover project context:
 
 **Project instructions:** Read `./CLAUDE.md` if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.
 
+**Self-improvement lessons:** Read `.planning/LESSONS.md` if it exists — accumulated lessons from past executions on this codebase. Apply them proactively to avoid known mistakes before they become deviations.
+
 **Project skills:** Check `.agents/skills/` directory if it exists:
 1. List available skills (subdirectories)
 2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
@@ -356,6 +358,57 @@ Or: "None - plan executed exactly as written."
 **Auth gates section** (if any occurred): Document which task, what was needed, outcome.
 </summary_creation>
 
+<self_improvement>
+After documenting deviations in SUMMARY.md, extract lessons to improve future agent runs.
+
+**Only run when deviations occurred** — skip entirely if "None - plan executed exactly as written."
+
+**For each deviation (Rule 1-3), determine the lesson type:**
+
+- **Codebase Pattern:** Something specific to THIS project's setup, conventions, or architecture
+- **Common Mistake:** A recurring coding issue agents should fix proactively before it happens
+
+**Write or update `.planning/LESSONS.md`.**
+
+If the file does not exist, create it first using the Write tool:
+
+```markdown
+# MAXSIM Self-Improvement Lessons
+
+> Auto-updated by MAXSIM agents after each execution. Read this at the start of every planning and execution session.
+
+## Codebase Patterns
+<!-- Project-specific conventions, gotchas, and setup details discovered during execution -->
+
+## Common Mistakes
+<!-- Recurring issues agents should fix proactively — before they cause deviations -->
+
+## Planning Insights
+<!-- Scope, dependency, or requirement gaps that planners should anticipate -->
+```
+
+Then append new lessons under the matching section using the Edit tool.
+
+**Lesson format:**
+```
+- [YYYY-MM-DD] [{phase}-{plan}] {actionable lesson — specific, avoidable, codebase-aware}
+```
+
+**Examples of good lessons:**
+- `[2026-02-26] [01-02] All API routes require CORS headers — add cors middleware to every new Express route`
+- `[2026-02-26] [02-01] user.profile can be null — always guard with ?. before accessing nested fields`
+- `[2026-02-26] [03-02] bun is the package manager here (not npm) — use bun run, bun add, bun install`
+
+**Examples of bad lessons (too generic — do not add):**
+- "Always add error handling" — not codebase-specific
+- "Check for null values" — not actionable enough
+
+**Rules:**
+- Cap at 3 new lessons per execution — choose the most codebase-specific
+- Check for existing similar lessons before appending to avoid duplicates
+- Append to the existing file using Edit, never overwrite
+</self_improvement>
+
 <self_check>
 After writing SUMMARY.md, verify claims before proceeding.
 

package/dist/assets/templates/agents/maxsim-plan-checker.md

@@ -31,6 +31,8 @@ Before verifying, discover project context:
 
 **Project instructions:** Read `./CLAUDE.md` if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.
 
+**Self-improvement lessons:** Read `.planning/LESSONS.md` if it exists — accumulated lessons from past executions. Use planning insights as an additional verification dimension: flag plans that repeat known gap patterns or ignore documented codebase conventions.
+
 **Project skills:** Check `.agents/skills/` directory if it exists:
 1. List available skills (subdirectories)
 2. Read `SKILL.md` for each skill (lightweight index ~130 lines)

package/dist/assets/templates/agents/maxsim-planner.md

@@ -33,6 +33,8 @@ Before planning, discover project context:
 
 **Project instructions:** Read `./CLAUDE.md` if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.
 
+**Self-improvement lessons:** Read `.planning/LESSONS.md` if it exists — accumulated lessons from past executions on this codebase. Apply planning insights proactively: avoid known gaps, include wiring tasks for patterns that historically broke, reference codebase-specific conventions in task actions.
+
 **Project skills:** Check `.agents/skills/` directory if it exists:
 1. List available skills (subdirectories)
 2. Read `SKILL.md` for each skill (lightweight index ~130 lines)

package/dist/assets/templates/agents/maxsim-verifier.md

@@ -16,6 +16,12 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool t
 **Critical mindset:** Do NOT trust SUMMARY.md claims. SUMMARYs document what Claude SAID it did. You verify what ACTUALLY exists in the code. These often differ.
 </role>
 
+<project_context>
+Before verifying, load project context:
+
+**Self-improvement lessons:** Read `.planning/LESSONS.md` if it exists — accumulated lessons from past executions. Use planning insights to sharpen your verification focus (e.g., known stub patterns, wiring gaps common in this codebase).
+</project_context>
+
 <core_principle>
 **Task completion ≠ Goal achievement**
 
@@ -470,6 +476,49 @@ Automated checks passed. Awaiting human verification.
 
 </output>
 
+<self_improvement>
+After writing VERIFICATION.md, if status is `gaps_found`, extract planning lessons.
+
+**Purpose:** Help future planners anticipate gaps that planning typically misses on this codebase.
+
+**For each gap, determine the root cause:**
+- Artifact completely missing → planner assumed it would appear as a side effect of another task
+- Artifact is a stub → executor left a placeholder; planner needs explicit `min_lines` in must_haves
+- Wiring broken → component exists but not connected; planner should add an explicit wiring task
+
+**Append to `.planning/LESSONS.md`** under `## Planning Insights` using the Edit tool.
+
+If `.planning/LESSONS.md` does not exist, create it with the Write tool using this header:
+
+```markdown
+# MAXSIM Self-Improvement Lessons
+
+> Auto-updated by MAXSIM agents after each execution. Read this at the start of every planning and execution session.
+
+## Codebase Patterns
+<!-- Project-specific conventions, gotchas, and setup details discovered during execution -->
+
+## Common Mistakes
+<!-- Recurring issues agents should fix proactively — before they cause deviations -->
+
+## Planning Insights
+<!-- Scope, dependency, or requirement gaps that planners should anticipate -->
+```
+
+**Lesson format:**
+```
+- [YYYY-MM-DD] [verifier:{phase}] {what was missed and how future planners can prevent it}
+```
+
+**Examples of good planning insights:**
+- `[2026-02-26] [verifier:03] Auth middleware was missing even though routes required it — always include auth wiring as an explicit task when plans touch protected endpoints`
+- `[2026-02-26] [verifier:02] ChatList component was a stub (< 20 lines) — set min_lines ≥ 30 in must_haves for components that render data`
+
+**Only add if the gap reveals a repeatable planning pattern** — not a one-off typo. Cap at 2 lessons per verification.
+
+**Do not commit LESSONS.md** — the orchestrator handles committing phase artifacts.
+</self_improvement>
+
 <critical_rules>
 
 **DO NOT trust SUMMARY claims.** Verify the component actually renders messages, not a placeholder.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "maxsimcli",
-  "version": "3.3.1",
+  "version": "3.5.0",
   "private": false,
   "description": "A meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini and Codex by MayStudios.",
   "bin": {