@lifeaitools/rdc-skills 0.24.13 → 0.24.14

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "rdc",
-  "version": "0.24.13",
+  "version": "0.24.14",
   "description": "RDC typed-agent dispatch skill suite for Claude Code — plan, build, review, overnight unattended builds with work-item tracking and TDD enforcement.",
   "author": {
     "name": "LIFEAI",

package/commands/help.md

@@ -1,90 +1,72 @@
 ---
 name: rdc:help
 description: >-
-  Usage `rdc:help` or `rdc` — selection menu of all rdc:* skills with their full argument syntax. Use when unsure which command to invoke or what args it takes.
+  Usage `rdc:help` or `rdc` — manifest-driven menu of all rdc:* skills with
+  argument syntax, requirements, decision hints, and direct MCP/curl access.
 ---
 
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> **Output contract:** Checklist/table output only. No raw MCP/JSON/log dumps.
 
+# rdc:help — Manifest-Driven Command Reference
 
-# rdc:help — Command Reference
+Print a concise command reference from the plugin manifest, then stop. Do not
+ask which command to run unless the user explicitly asks for a recommendation.
 
-Print the full usage menu below verbatim, then ask the project lead which command to run.
+## Source Of Truth
 
-## Workflow — the RDC loop
+Resolve the manifest in this order and use the first existing file:
 
-| Command | Usage |
-|---|---|
-| `rdc:preplan` | `rdc:preplan <topic> [--unattended]` — research, no code |
-| `rdc:plan` | `rdc:plan <topic> [--unattended]` — architecture + epic/tasks |
-| `rdc:build` | `rdc:build <epic-id\|topic> [--unattended]` — dispatch agents, commit, close items |
-| `rdc:review` | `rdc:review [--unattended]` — typecheck, tests, fix, commit |
-| `rdc:report` | `rdc:report [--unattended]` — write `.rdc/reports/YYYY-MM-DD.md` |
-| `rdc:overnight` | `rdc:overnight [epic-id\|label=X]` — chain preplan→plan→build→review→report |
-| `rdc:status` | `rdc:status` — read-only dashboard |
-| `rdc:fixit` | `rdc:fixit <description>` — bypass the loop, <5 files / <30 min |
+1. `{PLUGIN_ROOT}/.claude-plugin/plugin.json`
+2. `C:/Dev/rdc-skills/.claude-plugin/plugin.json`
+3. `~/.claude/plugins/cache/rdc-skills/rdc-skills/latest/.claude-plugin/plugin.json`
 
-## Ops
+Read `skills_meta` from the manifest. Group entries by `category` in this order:
+`planning`, `build`, `deploy`, `release`, `dev-loop`, `reporting`, `tooling`,
+`infra`.
 
-| Command | Usage |
-|---|---|
-| `rdc:deploy` | `rdc:deploy <slug> [build-id]` · `rdc:deploy new <slug>` · `rdc:deploy diagnose <slug>` · `rdc:deploy audit [--fix]` |
-| `rdc:release` | `rdc:release <repo> [version]` · `rdc:release <repo> --patch\|--minor\|--major` · `rdc:release <repo> --dry-run` |
+For each row, show:
 
-## Planning ↔ CLI bridge
+```text
+{slash}  —  {usage}  —  needs: {requires or "(none)"}  —  cf: {yes|no}
+```
+
+At the end, render a short decision tree from `skills_meta[].triggers`.
 
-| Command | Usage |
-|---|---|
-| `rdc:handoff` | `rdc:handoff <topic>` — finalize plan → work items for CLI |
-| `rdc:prototype` | `rdc:prototype <description>` — JSX mock for review |
-| `rdc:workitems` | `rdc:workitems <add\|update\|done\|list\|epics> [args]` |
-| `rdc:collab` | `rdc:collab --session <id>` — claude.ai bidirectional relay |
-| `rdc:design` | `rdc:design <command\|brief>` — RDC/Studio design, tokens, palettes, themes, Rampa CLI |
+If the manifest is unreachable, say `manifest fallback used` and render the
+static fallback table from `skills/help/SKILL.md`.
 
-## Agent guides (dispatched by rdc:build, not user-invocable)
+## Direct MCP / curl Access
 
-These live under `guides/agents/` — they are role playbooks the build skill spawns as sub-agents. You do NOT invoke them directly.
+Show this block after the command table so non-Claude callers have the same
+entry point:
 
-- `guides/agents/frontend.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/backend.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/data.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/design.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/infrastructure.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/content.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/cs2.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/viz.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/setup.md` — [agent-only — dispatched by rdc:build, not user-invocable]
-- `guides/agents/verify.md` — [agent-only — dispatched by rdc:build, not user-invocable]
+```text
+MCP endpoint: https://rdc-skills.regendevcorp.com/mcp
+Health:       curl -s https://rdc-skills.regendevcorp.com/health
+Header:       Accept: application/json, text/event-stream
+Tools:        rdc_skill_list, rdc_skill_search, rdc_skill_get
+Variants:     cli for Claude Code/Codex/local terminal; cloud for claude.ai
+```
 
-Each agent reads `.rdc/guides/agent-bootstrap.md` first, then its role guide.
+Minimal curl examples:
 
-## Decision tree
+```bash
+curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
+  -H 'Content-Type: application/json' \
+  -H 'Accept: application/json, text/event-stream' \
+  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rdc_skill_list","arguments":{}}}'
 
-```
-Project lead says → invoke
-─────────────────────────────────────────────────
-"research this" / "how do others do"    → rdc:preplan <topic>
-"plan this out" / "architect"           → rdc:plan <topic>
-"build it" / "go" / "execute"           → rdc:build <topic>
-"run overnight" / "while I sleep"       → rdc:overnight
-"quick fix" / "hotfix" / "typo"         → rdc:fixit <desc>
-"review" / "is it clean"                → rdc:review
-"report" / "summarize"                  → rdc:report
-"status" / "where are we"               → rdc:status
-"deploy" / "ship"                       → rdc:deploy <slug>
-"release" / "publish"                   → rdc:release <repo>
-"hand this off" / "give to agents"      → rdc:handoff
-"show me what it looks like"            → rdc:prototype
-"add to backlog" / "create a ticket"    → rdc:workitems
-"design/tokens/palette/theme"           → rdc:design <command>
-"what commands" / "what skills"         → rdc:help
+curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
+  -H 'Content-Type: application/json' \
+  -H 'Accept: application/json, text/event-stream' \
+  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"build","variant":"cli"}}}'
 ```
 
-## Hard rules (apply everywhere)
+## Hard Rules
 
-- NEVER `pnpm build` — crashes the machine. Typecheck with `npx tsc --noEmit`.
-- NEVER commit to `main` without explicit approval. Default branch is `develop`.
-- NEVER overlap agents on the same files.
-- ALWAYS update work items in real time via RPCs (see `.claude/rules/work-items-rpc.md`).
-- ALWAYS credentials via clauth daemon: `curl -s http://127.0.0.1:52437/get/<service>`.
+- `cf: yes` skills must consult CodeFlow before acting.
+- Never run `pnpm build` at monorepo root. Use scoped typecheck/tests.
+- Never commit to `main` without explicit approval.
+- Never overlap agents on the same files.
+- Update work items in real time for skills that require work-items RPCs.
+- Credentials come from clauth: `curl -s http://127.0.0.1:52437/v/<service>`.

package/git-sha.json

@@ -1,3 +1,3 @@
 {
-  "sha": "855a6b20f3ed897365cb835a6e7ad4a92b793d7a"
+  "sha": "090e6c4a0a643acca7ca0bfca384f43cc150dca9"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lifeaitools/rdc-skills",
-  "version": "0.24.13",
+  "version": "0.24.14",
   "description": "RDC typed-agent dispatch skill suite for Claude Code - plan, build, review, overnight builds",
   "keywords": [
     "claude-code",
@@ -35,7 +35,7 @@
     "rdc-design": "node scripts/rdc-design-cli.mjs",
     "test:hooks": "node scripts/test-rdc-hooks.mjs",
     "test:truth-gate": "node tests/run-evidence-gate.test.mjs && node tests/work-item-exit-gate-l2.test.mjs && node tests/work-item-exit-gate-l3.test.mjs && node tests/require-work-item-on-commit.test.mjs && node tests/harness-gates.test.mjs",
-    "test:acceptance": "node tests/acceptance.test.mjs && node tests/install-rdc-skills.test.mjs",
+    "test:acceptance": "node tests/acceptance.test.mjs && node tests/install-rdc-skills.test.mjs && node tests/help-surface.test.mjs",
     "acceptance": "node scripts/acceptance.mjs --changed",
     "test:mcp": "node tests/mcp.test.mjs",
     "test:mcp:remote": "node tests/mcp.test.mjs --remote",

package/skills/help/SKILL.md

@@ -21,7 +21,8 @@ description: "Usage `rdc:help` — Show all rdc:* skills with usage, requirement
 3. Group entries by `category` in this order: `planning, build, deploy, release, dev-loop, reporting, tooling, infra`.
 4. For each entry render one row: `{slash}  —  {usage}  —  needs: {requires.join(',')}  —  cf: {codeflow_required ? 'yes' : 'no'}`.
 5. Print a Decision Tree at the end that maps natural-language phrases to skills, derived from each entry's `triggers[]`.
-6. Hard rules section at the bottom (see below — verbatim).
+6. Print the Direct MCP / curl Access block so non-Claude callers have the same entry point.
+7. Hard rules section at the bottom (see below — verbatim).
 
 ## Required output format
 
@@ -86,6 +87,26 @@ RDC SKILLS — manifest: .claude-plugin/plugin.json @ v{version}
   "claude.ai relay" / "collab session"                  → /rdc:collab
   "palette" / "studio design" / "tokens"                → /rdc:design
 
+## Direct MCP / curl Access
+
+  MCP endpoint: https://rdc-skills.regendevcorp.com/mcp
+  Health:       curl -s https://rdc-skills.regendevcorp.com/health
+  Header:       Accept: application/json, text/event-stream
+  Tools:        rdc_skill_list, rdc_skill_search, rdc_skill_get
+  Variants:     cli for Claude Code/Codex/local terminal; cloud for claude.ai
+
+  List skills:
+  curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
+    -H 'Content-Type: application/json' \
+    -H 'Accept: application/json, text/event-stream' \
+    -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rdc_skill_list","arguments":{}}}'
+
+  Fetch a skill:
+  curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
+    -H 'Content-Type: application/json' \
+    -H 'Accept: application/json, text/event-stream' \
+    -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"build","variant":"cli"}}}'
+
 ## Hard rules
 
 - `cf: yes` skills MUST consult CodeFlow before acting. Hooks fail-closed on unreachable CodeFlow for these.

package/tests/help-surface.test.mjs

@@ -0,0 +1,33 @@
+#!/usr/bin/env node
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { dirname, join, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const root = resolve(__dirname, '..');
+
+const files = {
+  readme: join(root, 'README.md'),
+  skillHelp: join(root, 'skills', 'help', 'SKILL.md'),
+  commandHelp: join(root, 'commands', 'help.md'),
+};
+
+const docs = Object.fromEntries(
+  Object.entries(files).map(([key, file]) => [key, readFileSync(file, 'utf8')]),
+);
+
+for (const [name, text] of Object.entries(docs)) {
+  assert.match(text, /https:\/\/rdc-skills\.regendevcorp\.com\/mcp/, `${name} must expose production MCP endpoint`);
+  assert.match(text, /Accept: application\/json, text\/event-stream/, `${name} must show Streamable HTTP Accept header`);
+  assert.match(text, /rdc_skill_list/, `${name} must mention rdc_skill_list`);
+  assert.match(text, /rdc_skill_get/, `${name} must mention rdc_skill_get`);
+  assert.doesNotMatch(text, /https:\/\/rdc-skills\.dev\.regendevcorp\.com\/mcp/, `${name} must not point callers at dev MCP`);
+}
+
+assert.match(docs.skillHelp, /manifest-driven/i, 'skill help should be manifest-driven');
+assert.match(docs.commandHelp, /manifest-driven/i, 'command help should be manifest-driven');
+assert.doesNotMatch(docs.commandHelp, /Print the full usage menu below verbatim/, 'command help must not use stale static menu wording');
+assert.doesNotMatch(docs.commandHelp, /get\/<service>/, 'command help must use current clauth /v/<service> wording');
+
+console.log('help surface tests — PASS');