@maestria/kimi-code 0.4.6 → 0.4.8

package/README.md

@@ -6,12 +6,12 @@ A declarative, manifest-based Kimi Code plugin that ships 8 specialized skills (
 
 See [INSTALL.md](./INSTALL.md) for the full checklist. Quick start:
 
-```
-/plugins install https://github.com/agustinusnathaniel/maestria/tree/release/kimi-code
-mkdir -p ~/.kimi-code && cp rules/AGENTS.md ~/.kimi-code/AGENTS.md
+```bash
+pnpx maestria@latest install kimi-code
+pnpx maestria@latest status
 ```
 
-Alternatively, use the [maestria CLI](https://maestria.sznm.dev/cli/) to manage installation across all platforms from a single command.
+The CLI pulls `@maestria/kimi-code` from npm and extracts it into `~/.kimi-code/plugins/managed/maestria`.
 
 ## The 8 Skills at a Glance
 
@@ -62,15 +62,21 @@ Unlike OpenCode's plugin SDK, Kimi Code's plugin system is **declarative** - no
 - **No programmatic hooks** - the orchestrator skill carries the methodology, and Kimi Code's `[[hooks]]` blocks (user-managed) cover the rest.
 - **No custom subagent identity** - Kimi Code hardcodes `coder`/`explore`/`plan`. The 7 specialist identities are encoded as persona content in prompt templates.
 
-See [ADR-KC-001](../../docs/adr/kimi-code/ADR-KC-001-kimi-code-architecture.md) for the full design rationale.
+See the [architecture documentation](https://maestria.sznm.dev/kimi-code/architecture/) for the full design rationale.
 
 ## Updating
 
+```bash
+pnpx maestria@latest update kimi-code
 ```
-/plugins install https://github.com/agustinusnathaniel/maestria
+
+Updates follow the latest release by default. Pin to a specific version with:
+
+```bash
+pnpx maestria@latest update kimi-code@0.4.6
 ```
 
-Updates follow the latest release by default. Pin via tag or SHA for production work (see [INSTALL.md](./INSTALL.md)).
+See [INSTALL.md](./INSTALL.md) for details.
 
 ## Contributing
 
@@ -83,4 +89,3 @@ MIT
 ## Related
 
 - [`@maestria/opencode`](../opencode/README.md) - the OpenCode variant of this plugin (TypeScript SDK, programmatic hooks).
-- [ADR-KC-001](../../docs/adr/kimi-code/ADR-KC-001-kimi-code-architecture.md) - the architecture decision record for the Kimi Code plugin.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@maestria/kimi-code",
-  "version": "0.4.6",
+  "version": "0.4.8",
   "private": false,
   "description": "Maestria agent pack for Kimi Code - 8 specialized skills with swarm-aware orchestration",
   "keywords": [
@@ -34,7 +34,7 @@
     "provenance": true
   },
   "devDependencies": {
-    "@types/node": "^24",
+    "@types/node": "^26",
     "typescript": "^6.0.3"
   },
   "scripts": {

package/skills/commands/blitz/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: blitz
+description: "Fast implementation mode: skip recon/design unless unknown"
+type: prompt
+whenToUse: When the user types /blitz or includes "blitz" in their message for fast implementation.
+arguments: []
+---
+
+<!-- Auto-generated from @maestria/core. Do not edit directly.
+     Edit the canonical file at packages/core/agent-directives/ instead. -->
+
+**Skill profile:** `plan` - workflow mode command. You have Read, Glob, Grep, Bash, FetchURL, and WebSearch.
+
+[MODE: blitz]
+
+## MODE: blitz (Fast Implementation)
+
+Speed mode: skip reconnaissance and design gates. Go directly to builder for implementation. Only use adventurer if the codebase context is genuinely unknown (not as a default step). Skip reviewer unless the user explicitly requests review.

package/skills/commands/fein/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: fein
+description: "Full pipeline mode: recon, design, implement, review"
+type: prompt
+whenToUse: When the user types /fein or includes "fein" in their message to run the complete maestria pipeline.
+arguments: []
+---
+
+<!-- Auto-generated from @maestria/core. Do not edit directly.
+     Edit the canonical file at packages/core/agent-directives/ instead. -->
+
+**Skill profile:** `plan` - workflow mode command. You have Read, Glob, Grep, Bash, FetchURL, and WebSearch.
+
+[MODE: fein]
+
+## MODE: fein (Full Pipeline)
+
+Default role-based pipeline: thinker (recon/design/plan) -> worker (implementation) -> verifier (review). Verifier acceptance terminates the pipeline for that unit of work. Roles and order may adapt to task needs - this is the default, not a fixed requirement. Do NOT skip any phase unless the user explicitly overrides in the same turn.

package/skills/commands/sonar/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: sonar
+description: "Research-only mode: recon and design, no implementation"
+type: prompt
+whenToUse: When the user types /sonar or includes "sonar" in their message for research-only work.
+arguments: []
+---
+
+<!-- Auto-generated from @maestria/core. Do not edit directly.
+     Edit the canonical file at packages/core/agent-directives/ instead. -->
+
+**Skill profile:** `plan` - workflow mode command. You have Read, Glob, Grep, Bash, FetchURL, and WebSearch.
+
+[MODE: sonar]
+
+## MODE: sonar (Research Only)
+
+Research mode: reconnaissance and design only. Delegate to adventurer (recon) followed by architect or planner (analysis/design). STOP after delivering findings and design. Do NOT implement, write code, or create any production files.