Installation & Setup
@maestria/kimi-code is a declarative Kimi Code plugin - a manifest, a directory of skill files, and a global rules file. The plugin is loaded by Kimi Code at session start, and the orchestrator skill auto-injects the methodology.
Prerequisites
Section titled “Prerequisites”- Kimi Code v0.12.0+ - required for first-class
AgentSwarmsupport. On older versions, the orchestrator skill still works, but the swarm guidance falls back to singleAgentcalls. - Node.js 18+ - required for
npm packused by the CLI to install the plugin.
Installation via CLI (Recommended)
Section titled “Installation via CLI (Recommended)”The maestria CLI provides a unified interface for installing and managing maestria plugins across all supported platforms:
# Install for this platformnpx maestria install kimi-code# Install for this platformpnpx maestria install kimi-code# Install for this platformyarn dlx maestria install kimi-code# Verify installationnpx maestria status# Verify installationpnpx maestria status# Verify installationyarn dlx maestria statusAlternative: Manual setup
-
Install the plugin
The plugin is distributed via npm. The maestria CLI downloads and extracts it directly:
Terminal window npx maestria install kimi-codeTerminal window pnpx maestria install kimi-codeTerminal window yarn dlx maestria install kimi-codeThis runs
npm pack @maestria/kimi-code@latestand extracts the tarball into~/.kimi-code/plugins/managed/maestria, then copies the global rules to~/.kimi-code/AGENTS.md.Alternatively, you can install directly from npm with the same commands used internally:
Terminal window mkdir -p ~/.kimi-code/plugins/managed/maestrianpm pack @maestria/kimi-code@latest --pack-destination /tmptar -xzf /tmp/maestria-kimi-code-*.tgz -C ~/.kimi-code/plugins/managed/maestria --strip-components=1cp ~/.kimi-code/plugins/managed/maestria/rules/AGENTS.md ~/.kimi-code/AGENTS.mdrm -f /tmp/maestria-kimi-code-*.tgz -
Verify global rules (REQUIRED)
The maestria CLI copies the bundled
rules/AGENTS.mdto~/.kimi-code/AGENTS.mdduring install. Verify the file is in place:Terminal window ls -la ~/.kimi-code/AGENTS.md<!-- Some AGENTS.md files were truncated or omitted to fit the 32 KB budget --> -
Add lifecycle hooks to
config.toml(recommended)Open
~/.kimi-code/config.tomland add the following[[hooks]]blocks. These block destructive bash commands, inject a per-turn orchestrator reminder, and observe compaction cycles.# Block destructive bash commands[[hooks]]event = "PreToolUse"matcher = "Bash"command = "node ~/.kimi-code/hooks/block-dangerous-bash.mjs"timeout = 5# Per-turn orchestrator reminder[[hooks]]event = "UserPromptSubmit"matcher = ""command = "echo 'Maestria active: delegate via the orchestrator skill. Prefer adventurer for recon, architect for design, builder for implementation, diagnose for bugs, reviewer for QA, writer for docs, planner for multi-phase work.'"timeout = 5# Observe compaction cycles (observation-only)[[hooks]]event = "PreCompact"matcher = ".*"command = "echo \"compact start: $(date -Is)\" >> ~/.kimi-code/compact.log"timeout = 5[[hooks]]event = "PostCompact"matcher = ".*"command = "echo \"compact end: $(date -Is)\" >> ~/.kimi-code/compact.log"timeout = 5Save the companion script as
~/.kimi-code/hooks/block-dangerous-bash.mjs:let input = '';process.stdin.on('data', (chunk) => {input += chunk;});process.stdin.on('end', () => {const payload = JSON.parse(input);const command = payload.tool_input?.command ?? '';if (command.includes('rm -rf')) {console.error('Dangerous command detected, blocked');process.exit(2);}}); -
Optional: add review-only permission rules
Add the following to
~/.kimi-code/config.toml:# === Builder (coder) - read-only git + test commands ===# 6 separate rules because each `pattern` matches one command.# scope = "session-runtime" applies to the current session only.[[permission.rules]]decision = "allow"pattern = "Bash(git status*)"scope = "session-runtime"reason = "Builder: read-only git status"[[permission.rules]]decision = "allow"pattern = "Bash(git diff*)"scope = "session-runtime"reason = "Builder: read-only git diff"[[permission.rules]]decision = "allow"pattern = "Bash(git log*)"scope = "session-runtime"reason = "Builder: read-only git log"[[permission.rules]]decision = "allow"pattern = "Bash(npm test*)"scope = "session-runtime"reason = "Builder: run npm tests"[[permission.rules]]decision = "allow"pattern = "Bash(pnpm test*)"scope = "session-runtime"reason = "Builder: run pnpm tests"[[permission.rules]]decision = "allow"pattern = "Bash(npx tsc*)"scope = "session-runtime"reason = "Builder: run TypeScript type check"# === Review-only session - deny Write/Edit for every coder subagent ===# Do not use these session-wide denies while running builder or writer work.[[permission.rules]]decision = "deny"pattern = "Write"scope = "session-runtime"reason = "Review-only session: block all Write tools"[[permission.rules]]decision = "deny"pattern = "Edit"scope = "session-runtime"reason = "Review-only session: block all Edit tools"The
scopefield controls temporal granularity (turn-override,session-runtime,project,user) - it is not per-subagent granularity. Subagent tool lists come from the hardcoded profile (coder/explore/plan), not from per-agent rules. These rules provide session-wide tool enforcement for a review-only session; they cannot safely enforce reviewer boundaries while builder or writer work runs in the same session. -
Reload plugins and start a new session
Plugin changes only take effect in new sessions. After installing, run:
/reload/new -
Verify
In the fresh session, ask:
“Review these 5 files for security issues: src/auth.ts, src/api.ts, src/db.ts, src/routes.ts, src/middleware.ts”
The orchestrator should:
- Auto-load (via
sessionStart.skill). - Identify the work as ≥3 uniform items → use
AgentSwarmwith thereviewerpersona. - Dispatch a swarm across the 5 files.
If the orchestrator starts writing code directly, something is wrong with the install - check
/plugins listand confirm the session-start skill loaded. - Auto-load (via
Troubleshooting
Section titled “Troubleshooting”Orchestrator not loading
Section titled “Orchestrator not loading”- Check
/plugins list-maestriashould appear withenabled: true. - Check
~/.kimi-code/AGENTS.mdexists. - Restart Kimi Code completely (not just the session).
AgentSwarm not available
Section titled “AgentSwarm not available”- Requires Kimi Code v0.12.0+ for first-class swarm support. On older versions, the orchestrator’s swarm guidance falls back to parallel
Agentcalls.
AGENTS.md gets truncated
Section titled “AGENTS.md gets truncated”- The 32 KB budget is enforced by Kimi Code. Trim verbose sections or move detail into specialist SKILL.md files (loaded on demand via the
Skilltool).
Updating
Section titled “Updating”To update via the maestria CLI:
npx maestria update kimi-codepnpx maestria update kimi-codeyarn dlx maestria update kimi-codeTo pin to a specific version:
npx maestria update kimi-code@0.4.6pnpx maestria update kimi-code@0.4.6yarn dlx maestria update kimi-code@0.4.6Alternative: Manual update
The CLI uses npm to fetch the latest version. The same commands work manually:
rm -rf ~/.kimi-code/plugins/managed/maestriamkdir -p ~/.kimi-code/plugins/managed/maestrianpm pack @maestria/kimi-code@latest --pack-destination /tmptar -xzf /tmp/maestria-kimi-code-*.tgz -C ~/.kimi-code/plugins/managed/maestria --strip-components=1cp ~/.kimi-code/plugins/managed/maestria/rules/AGENTS.md ~/.kimi-code/AGENTS.mdrm -f /tmp/maestria-kimi-code-*.tgzUninstalling
Section titled “Uninstalling”npx maestria uninstall kimi-codepnpx maestria uninstall kimi-codeyarn dlx maestria uninstall kimi-code# or manually:rm -rf ~/.kimi-code/plugins/managed/maestria ~/.kimi-code/AGENTS.mdOptionally remove the [[hooks]] and [[permission.rules]] blocks from ~/.kimi-code/config.toml.
Next Steps
Section titled “Next Steps”- Quick Start - Your first session with the plugin
- Skill Reference - Detailed documentation for each skill