compound-workflow 0.1.9 → 0.1.10

package/README.md

@@ -132,7 +132,7 @@ Full detail: [src/AGENTS.md](src/AGENTS.md), [src/.agents/commands/](src/.agents
 Commands are the public API. Skills and agents are invoked by commands; you don’t call them directly.
 
 - **Workflow skills:** `brainstorming`, `file-todos`, `compound-docs`, `document-review`, `technical-review`, `git-worktree`, `agent-browser`, `process-metrics`, `xstate-actor-orchestration`.
-- **XState orchestration trigger:** Use `xstate-actor-orchestration` when complexity exceeds simple local state—UI container-as-orchestrator flows, backend/internal actor orchestration, receptionist/child-actor patterns, retries/timeouts/cancellation, or boolean-flag sprawl.
+- **State orchestration:** Use a state-orchestration skill when complexity exceeds simple local state (e.g. `xstate-actor-orchestration` per Skill Index)—UI container-as-orchestrator flows, backend/internal actor orchestration, receptionist/child-actor patterns, retries/timeouts/cancellation, or boolean-flag sprawl.
 - **Skill-local metadata:** Some skills may include tool-specific metadata under `src/.agents/skills/<skill>/agents/` (for example `openai.yaml`) when required by skill validation/runtime.
 - **Guardrail standards:** `data-foundations`, `pii-protection-prisma`, `financial-workflow-integrity`, `audit-traceability` — applied when work touches multi-tenant data, PII, money, or audit.
 - **Agents:** Used by plan, review, and work for research, lint, and validation (e.g. `repo-research-analyst`, `learnings-researcher`, `git-history-analyzer`, `agent-native-reviewer`).

package/package.json

@@ -1 +1 @@
-{"name":"compound-workflow","version":"0.1.9","description":"Clarify → plan → execute → verify → capture. One Install action for Cursor, Claude, and OpenCode.","license":"MIT","repository":{"type":"git","url":"git+https://github.com/cjerochim/compound-workflow.git"},"bin":{"compound-workflow":"scripts/install-cli.mjs"},"files":["src","scripts",".cursor-plugin",".claude-plugin","skills"],"engines":{"node":">=18"}}
+{"name":"compound-workflow","version":"0.1.10","description":"Clarify → plan → execute → verify → capture. One Install action for Cursor, Claude, and OpenCode.","license":"MIT","repository":{"type":"git","url":"git+https://github.com/cjerochim/compound-workflow.git"},"bin":{"compound-workflow":"scripts/install-cli.mjs"},"files":["src","scripts",".cursor-plugin",".claude-plugin","skills"],"engines":{"node":">=18"}}

package/src/.agents/commands/workflow/brainstorm.md

@@ -70,8 +70,8 @@ Use **AskQuestion** to suggest:
 - Planned spawned-child actors or receptionist-style actor lookup
 
 If these signals appear, note that `/workflow:plan` should evaluate
-`xstate-actor-orchestration`. Do not force architecture decisions in
-brainstorm.
+whether to load a state-orchestration skill (see Skill Index in
+AGENTS.md). Do not force architecture decisions in brainstorm.
 
 ---
 

package/src/.agents/commands/workflow/plan.md

@@ -90,10 +90,11 @@ Refine the idea through collaborative dialogue using **AskQuestion**:
 
 ### 0.5. State-Orchestration Fit Check (Decision in planning)
 
-Before finalizing architecture, decide whether to load
-`xstate-actor-orchestration`.
+Before finalizing architecture, decide whether to load an appropriate
+state-orchestration skill (see Skill Index in AGENTS.md; e.g.
+`xstate-actor-orchestration` when the stack uses that approach).
 
-Load it when complexity exceeds simple local state, especially for:
+Load one when complexity exceeds simple local state, especially for:
 
 - UI flows where a React container should orchestrate context/state and
   compose presentational components

package/src/.agents/commands/workflow/work.md

@@ -43,8 +43,9 @@ The input must be a plan file path.
 
 1.1. **Apply state-orchestration trigger (enforcement)**
 
-   If the plan or implementation involves XState/state-machine
-   orchestration, load `xstate-actor-orchestration` before coding.
+   If the plan or implementation involves state-machine or actor
+   orchestration, load the selected state-orchestration skill (see Skill
+   Index in AGENTS.md) before coding.
 
    Trigger examples:
 

package/src/AGENTS.md

@@ -85,6 +85,7 @@ High-risk triggers include: security, payments, privacy, data migration/backfill
 
 ## Routing Rules
 
+- **Capability-first in commands:** Core workflow command docs should name capabilities (problem shape), not specific libraries. Concrete skill resolution comes from the Skill Index.
 - Prefer existing project patterns before introducing new ones.
 - Always run local repo + institutional learnings research first for planning.
 - Run external best-practice/framework research based on fidelity and risk.