@lifeaitools/rdc-skills 0.35.18 → 0.35.20

package/guides/agent-bootstrap.md

@@ -119,9 +119,13 @@ pattern happened to catch.
 Playwright must still run headless in agent sessions. Do not use `--headed`,
 `--ui`, `codegen`, `open`, `show-report`, or `PWDEBUG=1`. Use list/dot/json
 reporters and saved trace/report artifacts instead of opening the Playwright
-UI. `foreground-process-gate.js` still hard-blocks this — it was never a
-terminal-launch-primitive question, so narrowing the launch rules above never
-touched it.
+UI. The managed environment guards
+`foreground-process-gate-playwright-headed` and
+`foreground-process-gate-playwright-ui` hard-block interactive forms; they do
+not block a project-owned headless `pnpm test:ui` command. Resolve Playwright
+from the target's pinned `@playwright/test` dependency, install its matching
+Chromium when absent, and run the named route/state test. A global CLI, route
+probe, or editor preview is not rendered evidence.
 
 Check the project overlay for specific language, package manager, and build constraints.
 
@@ -133,9 +137,21 @@ target's own declared build gates, or deploy to dev-PM2/npm-registry, you
 MUST use the real, tested `rdc-harness` CLI instead of hand-rolled bash/curl:
 
 ```bash
-node C:/Dev/rdc-harness/bin/rdc-harness.mjs <create|open|edit|build|deploy> <slug> --monorepo-root <your own worktree, never the shared checkout>
+npx --package=@lifeai/rdc-harness rdc-harness <create|open|edit|build|deploy> <slug> --monorepo-root <your own worktree, never the shared checkout>
 ```
 
+`rdc-harness` is distributed as `@lifeai/rdc-harness` on **GitHub Packages**,
+not npmjs (a different registry than `@lifeaitools/rdc-skills`). This needs
+`@lifeai:registry=https://npm.pkg.github.com` mapped in `.npmrc` with a GitHub
+PAT (clauth `github` service — repo/workflow/org scopes) as the registry auth
+token; check whether that mapping is already present (a machine that has
+already published or installed an `@lifeai` package usually has it globally)
+before assuming it needs to be created. Only if you are actively developing
+the harness itself does `node bin/rdc-harness.mjs ...` from inside a
+`C:/Dev/rdc-harness` checkout apply — never hardcode that path as a skill's
+default invocation; it exists on exactly one machine and defeats the point of
+a published package.
+
 One JSON receipt per call, exit 0/1 — use it as evidence for whatever
 checklist/commit step it satisfies. This is a genuinely FORCED requirement,
 not a suggestion: a skill that hand-rolls its own create/open/build/deploy
@@ -144,9 +160,12 @@ policy exists to stop.
 
 This does NOT apply to a skill with no create/open/build/deploy step at all
 (status/report/help/analysis/media/conversation skills) — do not invent one.
-`open`/`edit` require `RDC_HARNESS_ISSUER_SECRET` set explicitly, no default.
-`deploy` has zero Coolify awareness (Coolify stays `rdc:deploy`'s own path)
-and no live co-editing surface outside `site-html`/`site-ts` targets.
+**Corrected 2026-09-06:** `open`/`edit` do NOT require `RDC_HARNESS_ISSUER_SECRET`
+for a local call — a local `open`/`edit` returns a scoped handle (`signed:
+false`) and mints nothing; that env var only matters for an off-box actor
+(e.g. claude.ai) reaching in over the signed-binding path. `deploy` has zero
+Coolify awareness (Coolify stays `rdc:deploy`'s own path) and no live
+co-editing surface outside `site-html`/`site-ts` targets.
 
 ---
 

package/guides/agents/backend.md

@@ -1,104 +1,104 @@
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-> **Sandbox contract:** This guide honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag.
-
-
-# rdc:backend — Backend Agent
-
-## Mandatory First Step
-
-Read the guide before ANY code:
-```
-{PROJECT_ROOT}/.rdc/guides/backend.md
-(fallback: {PROJECT_ROOT}/.rdc/guides/backend.md)
-```
-
-## Database Client — One Pattern Per Context
-
-```ts
-// Server component / API route
-import { createServerClient } from "@regen/supabase";
-const supabase = await createServerClient();
-
-// Client component
-import { createBrowserClient } from "@regen/supabase";
-const supabase = createBrowserClient();
-```
-
-Non-public schemas:
-```ts
-const { data } = await supabase.schema("custom").from("table_name").select("*");
-```
-
-## Credentials — Daemon First
-
-```bash
-curl -s http://127.0.0.1:52437/get/<service>
-```
-- Never hardcode credentials
-- Never print keys to stdout
-- If daemon is down: report BLOCKED — do not work around it
-
-## Work Items — RPC Only
-
-```sql
--- Read epics
-SELECT get_open_epics();
-
--- Create
-SELECT insert_work_item(
-  p_title := 'Task title',
-  p_priority := 'high',
-  p_parent_id := '<epic-uuid>'::uuid,
-  p_source := 'agent'
-);
-
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+> **Sandbox contract:** This guide honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag.
+
+
+# rdc:backend — Backend Agent
+
+## Mandatory First Step
+
+Read the guide before ANY code:
+```
+{PROJECT_ROOT}/.rdc/guides/backend.md
+(fallback: {PROJECT_ROOT}/.rdc/guides/backend.md)
+```
+
+## Database Client — One Pattern Per Context
+
+```ts
+// Server component / API route
+import { createServerClient } from "@regen/supabase";
+const supabase = await createServerClient();
+
+// Client component
+import { createBrowserClient } from "@regen/supabase";
+const supabase = createBrowserClient();
+```
+
+Non-public schemas:
+```ts
+const { data } = await supabase.schema("custom").from("table_name").select("*");
+```
+
+## Credentials — Daemon First
+
+```bash
+curl -s http://127.0.0.1:52437/get/<service>
+```
+- Never hardcode credentials
+- Never print keys to stdout
+- If daemon is down: report BLOCKED — do not work around it
+
+## Work Items — RPC Only
+
+```sql
+-- Read epics
+SELECT get_open_epics();
+
+-- Create
+SELECT insert_work_item(
+  p_title := 'Task title',
+  p_priority := 'high',
+  p_parent_id := '<epic-uuid>'::uuid,
+  p_source := 'agent'
+);
+
 -- Implementation agents submit report + CodeFlow post, then move to review
 SELECT update_work_item_status('<uuid>'::uuid, 'review', '["Implementation complete; ready for validator"]'::jsonb, '<agent-session-id>', 'agent');
-```
-
-**NEVER write raw INSERT/UPDATE against work items.**
-
-## API Route Pattern
-
-```ts
-import { createServerClient } from "@regen/supabase";
-import { NextResponse } from "next/server";
-
-export async function GET() {
-  const supabase = await createServerClient();
-  const { data, error } = await supabase.from("table").select("*");
-  if (error) return NextResponse.json({ error: error.message }, { status: 500 });
-  return NextResponse.json(data);
-}
-
-export async function POST(request: Request) {
-  const body = await request.json();
-  const supabase = await createServerClient();
-  const { data, error } = await supabase.from("table").insert(body).select().single();
-  if (error) return NextResponse.json({ error: error.message }, { status: 400 });
-  return NextResponse.json(data, { status: 201 });
-}
-```
-
-## Auth
-
-Use the auth helpers from your project's auth package for protected apps.
-
-## Schema-Driven Forms
-
-When working with schema-driven forms (common in dynamic CRUD), never hardcode columns.
-Use the schema table to drive form rendering instead.
-
-## Safety Rules
-
-- Branch: development branch — auto-commit after logical blocks
-- NEVER run `pnpm build`
-- NEVER overlap with other agents on the same files
-- Update work items in real time — not batch at end
-- Push after each logical block *(skip if `$RDC_TEST=1` — echo `[RDC_TEST] skipping git push` instead)*
-- Write tests FIRST — red → implement → green
+```
+
+**NEVER write raw INSERT/UPDATE against work items.**
+
+## API Route Pattern
+
+```ts
+import { createServerClient } from "@regen/supabase";
+import { NextResponse } from "next/server";
+
+export async function GET() {
+  const supabase = await createServerClient();
+  const { data, error } = await supabase.from("table").select("*");
+  if (error) return NextResponse.json({ error: error.message }, { status: 500 });
+  return NextResponse.json(data);
+}
+
+export async function POST(request: Request) {
+  const body = await request.json();
+  const supabase = await createServerClient();
+  const { data, error } = await supabase.from("table").insert(body).select().single();
+  if (error) return NextResponse.json({ error: error.message }, { status: 400 });
+  return NextResponse.json(data, { status: 201 });
+}
+```
+
+## Auth
+
+Use the auth helpers from your project's auth package for protected apps.
+
+## Schema-Driven Forms
+
+When working with schema-driven forms (common in dynamic CRUD), never hardcode columns.
+Use the schema table to drive form rendering instead.
+
+## Safety Rules
+
+- Branch: development branch — auto-commit after logical blocks
+- NEVER run `pnpm build`
+- NEVER overlap with other agents on the same files
+- Update work items in real time — not batch at end
+- Push after each logical block *(skip if `$RDC_TEST=1` — echo `[RDC_TEST] skipping git push` instead)*
+- Write tests FIRST — red → implement → green

package/guides/agents/content.md

@@ -1,94 +1,94 @@
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-
-# rdc:content — Content Agent
-
-## Mandatory First Step
-
-Read the guide before writing ANY copy:
-```
-{PROJECT_ROOT}/.rdc/guides/content.md
-(fallback: {PROJECT_ROOT}/.rdc/guides/content.md)
-```
-
-## Core Message Development
-
-Before writing any copy:
-
-1. Define the lead word or core concept (e.g., "Stewardship", "Community", "Trust")
-2. State the core message in 1-2 sentences
-3. List language to always use
-4. List language to never use
-5. Define target audiences and key messages for each
-
-## Language Rules Pattern
-
-### Always Use
-- Core concept words (replace vague synonyms)
-- Specific, measurable terms
-- Active voice where possible
-- Real data, not approximations
-
-### Never Use
-| Avoid | Use Instead |
-|-------|-------------|
-| Vague concept | Specific term |
-| Passive construction | Active voice |
-| Clichéd term | Domain-specific language |
-
-## Regulatory Context
-
-Verify what regulations apply to your content before writing:
-- Never guarantee results or returns
-- Use ranges and targets, not promises
-- Include necessary disclaimers
-- Maintain transparency about assumptions
-
-## Audience Segments
-
-Define key audiences and their primary concerns:
-- What matters to this group?
-- What is their current perception?
-- What action do you want them to take?
-
-## Key Facts
-
-Maintain a source-of-truth list:
-- Financial figures
-- Timelines
-- Commitments
-- Metrics
-
-Never invent these — always verify.
-
-## Tone Template
-
-- Authority level: high/medium/low
-- Formality: formal/casual
-- Technical depth: detailed/accessible
-- Emotion: neutral/passionate
-- Speed: short/long form
-
-## Content Queue (save to database)
-
-```sql
-INSERT INTO content_queue (title, content_type, status, draft_body)
-VALUES (
-  'Email subject or article title',
-  'email_sequence',  -- or: social_post, article, newsletter, landing_copy
-  'draft',
-  '...'
-);
-```
-
-## Safety Rules
-
-- Never invent data — verify all figures
-- Never make legal claims — use "may be" language
-- Use prohibited words list when provided
-- Always include disclaimers for regulated content
-- Branch: development branch — commit content files to repo
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+
+# rdc:content — Content Agent
+
+## Mandatory First Step
+
+Read the guide before writing ANY copy:
+```
+{PROJECT_ROOT}/.rdc/guides/content.md
+(fallback: {PROJECT_ROOT}/.rdc/guides/content.md)
+```
+
+## Core Message Development
+
+Before writing any copy:
+
+1. Define the lead word or core concept (e.g., "Stewardship", "Community", "Trust")
+2. State the core message in 1-2 sentences
+3. List language to always use
+4. List language to never use
+5. Define target audiences and key messages for each
+
+## Language Rules Pattern
+
+### Always Use
+- Core concept words (replace vague synonyms)
+- Specific, measurable terms
+- Active voice where possible
+- Real data, not approximations
+
+### Never Use
+| Avoid | Use Instead |
+|-------|-------------|
+| Vague concept | Specific term |
+| Passive construction | Active voice |
+| Clichéd term | Domain-specific language |
+
+## Regulatory Context
+
+Verify what regulations apply to your content before writing:
+- Never guarantee results or returns
+- Use ranges and targets, not promises
+- Include necessary disclaimers
+- Maintain transparency about assumptions
+
+## Audience Segments
+
+Define key audiences and their primary concerns:
+- What matters to this group?
+- What is their current perception?
+- What action do you want them to take?
+
+## Key Facts
+
+Maintain a source-of-truth list:
+- Financial figures
+- Timelines
+- Commitments
+- Metrics
+
+Never invent these — always verify.
+
+## Tone Template
+
+- Authority level: high/medium/low
+- Formality: formal/casual
+- Technical depth: detailed/accessible
+- Emotion: neutral/passionate
+- Speed: short/long form
+
+## Content Queue (save to database)
+
+```sql
+INSERT INTO content_queue (title, content_type, status, draft_body)
+VALUES (
+  'Email subject or article title',
+  'email_sequence',  -- or: social_post, article, newsletter, landing_copy
+  'draft',
+  '...'
+);
+```
+
+## Safety Rules
+
+- Never invent data — verify all figures
+- Never make legal claims — use "may be" language
+- Use prohibited words list when provided
+- Always include disclaimers for regulated content
+- Branch: development branch — commit content files to repo

package/guides/agents/cs2.md

@@ -1,56 +1,56 @@
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-
-# rdc:cs2 — CS 2.0 Agent
-
-## Mandatory First Step
-
-Read the guide before ANY code:
-```
-{PROJECT_ROOT}/.rdc/guides/cs2.md
-(fallback: {PROJECT_ROOT}/.rdc/guides/cs2.md)
-```
-
-Also read the master spec:
-```
-{PROJECT_ROOT}/docs/systems/cs2/cs2-master-spec.md
-{PROJECT_ROOT}/docs/systems/cs2/package-map.md
-```
-
-## The Paradigm Check
-
-**Before writing ANY code, ask:**
-> "Is this building a new computational primitive, or am I wiring a UI to a database?"
-
-If the latter — STOP. That is CS 1.0 thinking. Route to `rdc:frontend` + `rdc:backend`.
-
-## Package Dependency Graph
-
-Respect this — never create circular deps:
-
-```
-Layer 0 (roots): cs2, core-primitive-1, core-primitive-2
-Layer 1: system-a(core-primitive-1), system-b(core-primitive-2)
-Layer 2: advanced-system(system-a, system-b)
-```
-
-Apps depend on `@regen/` packages. **Apps never depend on each other.**
-
-## TypeScript — No `any`, No Escape Hatches
-
-CS 2.0 packages must be fully typed. If you hit a type boundary you cannot express,
-that is a signal the abstraction is wrong — fix the model, not the types.
-
-## Safety Rules
-
-- Branch: development branch — auto-commit per package
-- NEVER run `pnpm build` — use `npx tsc --noEmit --project packages/<n>/tsconfig.json`
-- Respect the dependency graph — no circular deps
-- Never self-modify governance weights from executing layers
-- All immutable proofs are permanent — never update committed data
-- NEVER overlap agents on the same package
-- Write tests FIRST — red → implement → green
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+
+# rdc:cs2 — CS 2.0 Agent
+
+## Mandatory First Step
+
+Read the guide before ANY code:
+```
+{PROJECT_ROOT}/.rdc/guides/cs2.md
+(fallback: {PROJECT_ROOT}/.rdc/guides/cs2.md)
+```
+
+Also read the master spec:
+```
+{PROJECT_ROOT}/docs/systems/cs2/cs2-master-spec.md
+{PROJECT_ROOT}/docs/systems/cs2/package-map.md
+```
+
+## The Paradigm Check
+
+**Before writing ANY code, ask:**
+> "Is this building a new computational primitive, or am I wiring a UI to a database?"
+
+If the latter — STOP. That is CS 1.0 thinking. Route to `rdc:frontend` + `rdc:backend`.
+
+## Package Dependency Graph
+
+Respect this — never create circular deps:
+
+```
+Layer 0 (roots): cs2, core-primitive-1, core-primitive-2
+Layer 1: system-a(core-primitive-1), system-b(core-primitive-2)
+Layer 2: advanced-system(system-a, system-b)
+```
+
+Apps depend on `@regen/` packages. **Apps never depend on each other.**
+
+## TypeScript — No `any`, No Escape Hatches
+
+CS 2.0 packages must be fully typed. If you hit a type boundary you cannot express,
+that is a signal the abstraction is wrong — fix the model, not the types.
+
+## Safety Rules
+
+- Branch: development branch — auto-commit per package
+- NEVER run `pnpm build` — use `npx tsc --noEmit --project packages/<n>/tsconfig.json`
+- Respect the dependency graph — no circular deps
+- Never self-modify governance weights from executing layers
+- All immutable proofs are permanent — never update committed data
+- NEVER overlap agents on the same package
+- Write tests FIRST — red → implement → green