nx/skills/rdr-accept/SKILL.md
Use when a gated RDR returned PASSED and you want to officially accept it for implementation
npx skillsauth add hellblazer/nexus rdr-acceptInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Accepts an RDR after it passes the gate. This is the author/reviewer decision point between gate validation and implementation.
/nx:rdr-accept003{id}-gate-latest from T2. Block if outcome is not PASSED.status: "accepted", accepted_date: "YYYY-MM-DD".status: draft to status: accepted, add accepted_date.self if empty.{rdr_dir}/README.md index.git add modified files.rdr-planning-context: mcp__plugin_nx_nexus__scratch(action="put", content="RDR {id}: planning context for {title}. RDR file: {rdr_file}", tags="rdr-planning-context,rdr-{id}"mcp__plugin_nx_nexus__nx_plan_audit — audit the plan against codebase. T1 scratch has rdr-planning-context tag.mcp__plugin_nx_nexus__nx_enrich_beads — enrich beads with execution context (+ audit findings from T1), write epic bead ID to T2.relates links:
mcp__plugin_nx_nexus-catalog__search(query="<rdr-title-keywords>", content_type="rdr")mcp__plugin_nx_nexus-catalog__link(from_tumbler="<this-rdr-title>", to_tumbler="<related-rdr-tumbler>", link_type="relates", created_by="rdr-accept")Steps 1-6 execute directly — no agent delegation. Step 7 (planning handoff) uses one agent dispatch and two MCP tool calls sequentially:
strategic-planner (Agent tool) — creates plan and beadsmcp__plugin_nx_nexus__nx_plan_audit — validates plan against codebase (RDR-080: no agent spawn)mcp__plugin_nx_nexus__nx_enrich_beads — enriches beads with execution context (RDR-080: no agent spawn)The accept skill writes a T1 scratch entry tagged rdr-planning-context before step 1.
Important: Step 2 (T2 status: accepted write) must complete before Step 7 (planner dispatch) to satisfy RDR-024 Guardrail 2 (strategic-planner pre-check warns if RDR not accepted).
Outputs produced directly by this skill (Steps 1-6):
status: accepted, accepted_date), regenerated {rdr_dir}/README.mdmcp__plugin_nx_nexus__nx_plan_audit → mcp__plugin_nx_nexus__nx_enrich_beads (optional, user-confirmed, orchestrated by this skill — RDR-080)development
Use when critiquing / auditing / reviewing a change set against decision history — tries the review plan library first (catalog lookup → decision-evolution traversal → extract → compare), falls through to /nx:query if nothing matches
documentation
Use when doing design / architecture / planning work that walks from prose (RDRs, docs, knowledge) into the modules implementing a concept
development
Use when surveying the plan library's runtime metrics to propose plans for promotion to a higher scope — advisory-only; dispatches the plan-promote-propose meta-seed (no lifecycle ops — those ship in RDR-079)
business
Use when inspecting plan runtime metrics or enumerating dimension-registry usage — dispatches plan_match with dimensions={verb:plan-inspect}; strategy:default reports per-plan metrics, strategy:dimensions reports registry usage counts