configure-branches — Claude Code command for nurture branching logic
The configure-branches command for Claude Code generates step-by-step instructions for configuring branching, personalization, and automations in nurture campaigns.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/configure-branches.mdWhat configure-branches does
The command takes a journey name or blueprint ID, a target MAP/CRM platform, and optional asset and webhook lists. Output includes an implementation checklist, a QA evidence matrix with test profiles and expected results, a changelog template, and a plan entry written to .claude/plans/plan-<timestamp>.json for audit traceability.
The workflow runs five phases: blueprint sync, branch mapping to platform-specific steps (smart lists, decision splits, wait steps, webhook calls), personalization token wiring, QA plan assembly, and documentation with rollback notes. Where QA and personalization can run in parallel, the command explicitly marks a diamond segment and defines merge points. With --qa true (the default), screenshot and log collection steps are added as evidence.
Three sub-agents are invoked: marketing-ops-partner, personalization-logic, and nurture-testing. Each failed automation retries at most 2 times; two guardrail breaches on unsubscribe rates or latency within 48h trigger escalation to Marketing and Sales leadership. Access to the target MAP platform is required before Branch Mapping can complete.
What it helps with
- translate a journey diagram into platform-specific steps for Marketo, HubSpot, or Braze
- wire dynamic content tokens and conditional logic across branches
- build a QA matrix with seed profiles and edge-case scenarios
- generate a changelog and rollback plan for every branching change
- connect external webhooks to nurture journey steps
Example prompts for the agent
- Run
/lead-nurture-orchestration:configure-branches --journey "MM Onboarding" --platform marketo --qa true - Set up branches for the
Q3 Re-engagementjourney on HubSpot and wire webhooks fromwebhooks.json - Generate a QA matrix and rollback plan for the Braze journey
Trial Activation
How to install configure-branches
Manually: put the files in place
.claude/commands/configure-branches.mdCall it with /configure-branches. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/configure-branches.mdCall it with /prompts:configure-branches. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/configure-branches.prompt.mdManually: put the files in place
.gemini/commands/configure-branches.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about configure-branches
How do I install configure-branches in Claude Code?
Place the command file at .claude/commands/configure-branches.md inside your project. Claude Code picks it up automatically.
What does configure-branches do?
It generates step-by-step build instructions for nurture branching logic, personalization, and automations on a chosen MAP/CRM platform, along with a QA evidence matrix and changelog template.
Is the --qa flag on by default?
Yes, --qa defaults to true, so the evidence-gathering steps and QA matrix are always included. Pass --qa false to remove them from the output.
Source text
configure-branches.md · Apache-2.0
--- name: configure-branches description: Generates implementation instructions for nurture branching logic, personalization rules, and automations. usage: /lead-nurture-orchestration:configure-branches --journey "MM Onboarding" --platform marketo --qa true --- # Command: configure-branches ## Inputs - **journey** – reference name or existing blueprint ID. - **platform** – MAP/CRM platform (Marketo, HubSpot, Braze, Iterable, Pardot, Customer.io, SF Automations). - **qa** – include QA + evidence steps (default true). - **assets** – optional asset list to wire. - **webhooks** – optional external integrations to include. ### GTM Agents Pattern & Plan Checklist > Lifted from GTM Agents orchestrator practices @puerto/plugins/orchestrator/README.md#112-325. - **Pattern selection**: Most branching config is a **pipeline** continuation of design-nurture. If QA + personalization can run parallel, explicitly log a **diamond** segment and define merge points. - **Plan schema**: Update `.claude/plans/plan-<timestamp>.json` (or create if standalone) with branch IDs, step references, tokens, webhook payloads, QA scenarios, and error handling. Note dependencies (assets, webhooks) and success criteria (activation %, latency). - **Tool hooks**: Use `docs/gtm-essentials.md` stack—Serena for MAP diffs, Context7 for platform docs, Sequential Thinking for post-flight retro, Playwright for landing/app QA. - **Guardrails**: Default retry limit = 2 per failed automation. Escalate Marketing Ops Partner → Nurture Architect → RevOps if QA evidence fails or compliance issues appear. - **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before publishing to ensure agents, dependencies, and deliverables are confirmed. ## Workflow 1. **Blueprint Sync** – pull journey diagram, triggers, suppression, personalization tokens. 2. **Branch Mapping** – translate logic into platform-specific steps (smart lists, decision splits, wait steps, webhook calls). 3. **Personalization Wiring** – define tokens, dynamic content blocks, conditional logic. 4. **QA & Evidence** – build test plan (seed profiles, edge cases, fallback paths) with screenshots/logs. 5. **Documentation** – produce build guide, change log, rollback plan. ## Outputs - Implementation checklist with step-by-step instructions. - QA/evidence matrix (test profile, scenario, expected result, status). - Change log template + rollback notes. - Plan JSON entry stored/updated in `.claude/plans` for traceability. ## Agent/Skill Invocations - `marketing-ops-partner` – executes platform build. - `personalization-logic` skill – ensures conditional content is accurate. - `nurture-testing` skill – enforces QA rigor. ## GTM Agents Safeguards - **Fallback agents**: document substitutes (e.g., Marketing Ops Partner covering testing) if specialists unavailable. - **Escalation triggers**: if unsubscribe/spam complaints or latency guardrails breach twice in 48h, trigger lifecycle rip-cord and notify Marketing + Sales leadership. - **Plan maintenance**: each branching change requires updating plan JSON + change log; reference in status packets to keep audit trail aligned with GTM Agents standards. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents