Content
> **Read in:** 🇺🇸 [English](README.md) | 🇧🇷 [Português (Brasil)](README.pt-BR.md)
# Claude Code MaxVision
[](LICENSE)
[](https://github.com/produtoramaxvision/maxvision/actions)
[](CHANGELOG.md)
Dynamic skill + subagent orchestrator for Claude Code — zero session-startup overhead, version integrity on autopilot, human-driven provisioning.
> **Pre-1.0 stability notice.** This plugin is in the `0.x.y` series. Breaking changes
> can land in minor versions until `1.0.0` ships. Pin to a specific tag if your
> automation depends on a particular hook/skill API shape. See [CHANGELOG.md](CHANGELOG.md)
> for migration notes on every release.
---
## Overview
MaxVision eliminates the 15k-token agent overhead in Claude Code 2.1.x by keeping 500+ specialist subagents and 4,000+ skills in an FTS5 catalog and materializing only what each task requires. The orchestrator reads your cheatsheets, audits locally installed components, checks upstream commits, and presents a single approval prompt before dispatching to the right agent with the right skills loaded.
**Three guarantees:**
- **Zero-overhead discovery** — BM25 full-text search across 500+ agents and 4,000+ skills. No cumulative agent descriptions in the system prompt; no session-startup overhead.
- **Version integrity on autopilot** — upstream commit check before every install or update. One-hour cache with `--force-check` bypass. Origin tracked in `.maxvision-source.json` per component.
- **Human-driven provisioning** — single approval prompt (`sim / all / skip-N / none`). Updates run before installs. Tier 4 entries require explicit per-line sign-off even in batch mode.
---
## Skills
| Skill | Purpose |
| --- | --- |
| `orchestrate` | Master entry point — 8-phase flow with clarity gate, multi-task split, lazy-load agents. |
| `route-task` | FTS5 + BM25 discovery; picks subagent + skills for the task. |
| `discover-skill` | Lookup missing skills in the curated catalog. |
| `discover-agent` | BM25/FTS5 lookup for agents by keyword. |
| `check-version` | Compare local `gitCommitSha` with upstream (cache 1h, `--force-check` bypass). |
| `update-component` | Apply upstream update to a skill or agent. |
| `install-skill` | Install via sparse-clone, marketplace, synthesis, or antigravity. |
| `install-agent` | Install agent on-demand (lazy-load model — `from_cache`, `sparse_clone`, `raw_url`). |
| `uninstall-agent` | Remove a lazy-installed agent (manual only; never auto-invoked). |
| `audit-local-skills` | Read-only inventory with redundancy detection and budget report. |
| `synthesize-skill` | Create a custom `maxvision-<name>` skill from complementary upstream sources. |
| `refresh-catalog` | Re-fetch upstream metadata for the FTS5 catalog. |
---
## Slash Commands
40 commands across 5 categories, all under `/maxvision:`. Full reference: [docs/COMMANDS.md](docs/COMMANDS.md).
| Category | Commands |
| --- | --- |
| **Spec & Planning** | `spec-phase`, `discuss-phase`, `writing-plans`, `executing-plans`, `plan-phase` |
| **Execute & Ship** | `execute-phase`, `ship`, `verify-phase`, `pr-branch`, `complete-milestone` |
| **Review** | `code-review`, `pr-review`, `security-audit`, `qa`, `inbox` |
| **Lifecycle** | `progress`, `pause-work`, `resume-work`, `cleanup`, `health`, `forensics` |
| **Update** | `update [--force\|--json]`, `check-update [--force\|--json]` |
---
## Installation
### Option 1 — Marketplace (recommended)
```text
/plugin marketplace add produtoramaxvision/maxvision
/plugin install maxvision@maxvision
```
### Option 2 — Local development
```bash
git clone https://github.com/produtoramaxvision/maxvision.git
claude --plugin-dir ./maxvision
```
---
## Quick Start
```text
# Orchestrate a complex task
/maxvision:orchestrate refactor src/components/Foo.tsx to use shadcn Select and add unit tests
# Plan before coding
/maxvision:plan-phase --phase 2 --interactive
# Ship a completed phase
/maxvision:ship --phase 3
# Check for plugin updates
/maxvision:update --force
```
For the full guided walkthrough, see [docs/QUICKSTART.md](docs/QUICKSTART.md).
---
## How to invoke orchestrate
The `orchestrate` skill is the multi-domain dispatcher (10 phases P0..P10). It has **two** activation surfaces:
| Form | What it is | Notes |
| --- | --- | --- |
| `/maxvision:orchestrate <task>` | Canonical slash command (real) | The only real slash. Always works. Use in scripts, docs, and automations. Resolves through the plugin's `commands/` directory. |
| Natural-language mention or trigger phrase | Skill `when_to_use` auto-activation | When your prompt matches phrases like "use the best subagent for…", "tarefa complexa: …", "rote essa tarefa", or simply mentions "orchestrate" / "orquestre" in context, Claude reads the skill's `when_to_use` metadata and invokes `orchestrate` on its own. See the skill's frontmatter for the full trigger list. |
> **Note.** Plugin slash commands in Claude Code are namespaced — only `/maxvision:orchestrate` resolves through the plugin's command resolver. A bare `/orchestrate` typed in chat is **not** a real plugin slash command; it works (when it works) only because Claude's main thread recognizes the textual mention and dispatches through skill auto-activation. If you need a guaranteed dispatch in a script or automation, use the namespaced form.
There is **no LLM in any plugin hook** — auto-activation is driven by the skill's `when_to_use` metadata and Claude Code's main-thread interpretation, not by a subprocess classifier. Hooks in this plugin are 100% deterministic (regex / JSON / file IO). If you previously relied on a `UserPromptSubmit` LLM nudge, see the [v0.1.1 BREAKING CHANGE notes](CHANGELOG.md#011--2026-05-28) — the nudge was removed because subprocess hooks cannot inherit Claude Code's OAuth credentials, so the SDK call always failed.
---
## Statusline (optional)
MaxVision ships a Claude Code statusline showing: model · MaxVision state (milestone/status/phase) · directory · context-window progress bar. Composes with the **caveman** plugin automatically.
Activate by adding one entry to `~/.claude/settings.json`:
**Linux / macOS:**
```json
"statusLine": {
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/maxvision-statusline.sh"
}
```
**Windows:**
```json
"statusLine": {
"type": "command",
"command": "powershell -ExecutionPolicy Bypass -File \"${CLAUDE_PLUGIN_ROOT}/hooks/maxvision-statusline.ps1\""
}
```
Or run `/maxvision:setup-statusline` — the auto-install hook writes the correct absolute path for your platform.
---
## CLI Helpers
Four CLI tools are automatically in your `PATH` while the plugin is enabled. All validate identifiers against strict regexes before invoking external dependencies — path traversal and shell metacharacters are rejected with `rc=2`.
### `bin/maxvision-skills`
```bash
maxvision-skills list # list all local skills
maxvision-skills find <keyword> # search catalog + local by keyword
maxvision-skills check [--force] <comp> # version check (cached 1h)
maxvision-skills install <skill-id> # interactive install
maxvision-skills update <component> # interactive update
maxvision-skills audit # redundancy + budget + telemetry report
maxvision-skills search <query> # BM25 ranking against indexed skills
```
### `bin/maxvision-agents`
```bash
maxvision-agents list # list installed agents
maxvision-agents find <keyword> # search FTS5 catalog by keyword
maxvision-agents check [--force] <name> # version-check (sidecar vs upstream)
maxvision-agents audit # inventory + 15k-token budget estimate
maxvision-agents search <query> # top-10 BM25 ranking
```
### `bin/maxvision-dispatch`
```bash
maxvision-dispatch run <agent> "<task>" [--worktree] [--model=sonnet|opus|haiku]
maxvision-dispatch list # list maxvision-* agents available locally
maxvision-dispatch status # opens `claude agents` UI
maxvision-dispatch attach <session-id>
maxvision-dispatch logs <session-id>
```
### `bin/maxvision-sources`
```bash
maxvision-sources list # sources grouped by tier
maxvision-sources add <github-url> # add new source (autodetect metadata)
maxvision-sources verify <id> # reachability check + FTS5 stats
maxvision-sources rebuild # rebuild FTS5 index from sources
maxvision-sources stats # tier counts + install-method breakdown
```
---
## Troubleshooting
### Skill invisible after install (`paths:` bug — CC #49835)
Adding `paths: ["**/*.ts"]` to a skill frontmatter makes it undiscoverable in Claude Code ≥ 2.1.84 (upstream bug [#49835](https://github.com/anthropics/claude-code/issues/49835), open). **Workaround:** remove the `paths:` field; encode path-scoping in the `description` instead. This plugin's `validate.yml` CI blocks any PR adding `paths:` to a `SKILL.md`.
### `gh: command not found` / `jq: command not found`
Both must be in PATH for catalog operations and version checks:
- Windows: `winget install GitHub.cli jqlang.jq`
- macOS: `brew install gh jq`
- Linux: `apt-get install gh jq` / `dnf install gh jq`
Verify with `gh auth status` and `jq --version`.
---
## Requirements
- Claude Code ≥ 2.0
- `gh` CLI authenticated (`gh auth status`) — used by `check-version` and `install-agent`
- `jq` in PATH — used by version comparison and JSON parsing
- `npx` (Node ≥ 18) — only for the antigravity install path
---
## Hard Rules (Guardrails)
1. **Never installs or updates silently** — single approval prompt with `sim / all / skip-N / none`.
2. **`general-purpose` dispatch** is permitted only as Phase 8 fallback with full agent body injection. Set `MAXVISION_DISALLOW_GENERAL_PURPOSE=1` to opt out.
3. **Max 3–4 subagents in parallel** — prevents context pollution.
4. **Updates run before installs** — updates can change resolution of new installs.
5. **Tier 4 entries require per-line approval** even in batch mode.
6. **No `git pull` without `--ff-only`** — prevents accidental merges.
7. **No deletion of user-authored files** — only files installed by this orchestrator.
---
## Architecture
See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the 8-phase orchestration flow diagram, FTS5 indexing strategy, synthesis pipeline, cache layout, and `.maxvision-source.json` schema.
---
## Catalog of Sources
Four trust tiers documented in [docs/CATALOG-SOURCES.md](docs/CATALOG-SOURCES.md):
- **Tier 1 (Official Anthropic):** `anthropics/skills`
- **Tier 2 (Curated premium):** Antigravity, Composio, addyosmani, Obra, and others
- **Tier 3 (Domain-specific):** Trail of Bits, shadcn/ui, Expo, and others
- **Tier 4 (Evaluate with caution):** High-overlap or unmaintained sources
---
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md). Join the community:
| Channel | Best for |
| --- | --- |
| [Discord](https://discord.gg/XnbSGnXEv) | Real-time help, orchestration tips, pairing |
| [Discussions](https://github.com/produtoramaxvision/maxvision/discussions) | Design proposals, async Q&A |
| [Issues](https://github.com/produtoramaxvision/maxvision/issues) | Reproducible bugs and concrete feature requests |
Security findings → [SECURITY.md](SECURITY.md) — never public issues.
OpenSSF Scorecard: [securityscorecards.dev](https://securityscorecards.dev/viewer/?uri=github.com/produtoramaxvision/maxvision).
---
## Commercial Services
MaxVision offers premium support, custom skill catalog development, and AI workflow consulting for teams. See [docs/COMMERCIAL.md](docs/COMMERCIAL.md) for tiers and pricing. Contact: `contato@maxvision.com.br`.
---
## Changelog
See [CHANGELOG.md](CHANGELOG.md).
---
## License
MIT — see [LICENSE](LICENSE).
Third-party attributions: [LICENSES/THIRD-PARTY-NOTICES.md](LICENSES/THIRD-PARTY-NOTICES.md).
---
© 2026 [Produtora MaxVision](https://github.com/produtoramaxvision)
Connection Info
You Might Also Like
ai-native-pm-os
The exhaustive guide to mastering Claude for Product Managers. Build your...
Train-in-Silence
The first Task-Aware MCP server and automated VRAM calculator for LLM...
stacklit
108,000 lines of code. 4,000 tokens of index. One command makes any repo...
AppClaw
AI-powered mobile automation agent — describe what you want in plain...
pdf-mcp
Production-ready MCP server for PDF processing with intelligent caching....
kotadb
Local-only code intelligence API for AI developer workflows (Bun +...