configure-rules — Claude Code command for personalization rules
The configure-rules command takes personalization rules through data checks, decision setup, variant mapping, QA, and deployment. Use it to prepare changes for web and in-app channels.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/configure-rules.mdWhat configure-rules does
The command starts by checking profiles, data freshness, consent, and experiment dependencies. It then configures rules, weights, or model endpoints in MAP, CDP, or product tooling, and links each outcome to content, CTAs, and fallback experiences.
Next, it runs simulated checks and captures screenshots or logs; after deployment, it records versions, approvals, and a rollback plan. The plan goes in .claude/plans/plan-<timestamp>.json. Serena, Context7, Sequential Thinking, and Playwright are named for rule comparison, platform guidance, go/no-go reviews, and QA evidence. Deployment or QA retries are capped at 2, so repeated failures trigger escalation.
What it helps with
- check profiles, consent, and experiment dependencies before launch
- map rule outcomes to content and fallback experiences
- test decision trees with synthetic traffic
- record versions, approvals, and rollback steps
Example prompts for the agent
- Configure the rules for the “PLG Onboarding” initiative in staging for web and in-app:
/personalization-engine:configure-rules --initiative "PLG Onboarding" --environment staging --channels "web,in-app". - Deploy updated “PLG Onboarding” rules to production for web and in-app:
/personalization-engine:configure-rules --initiative "PLG Onboarding" --environment production --channels "web,in-app".
How to install configure-rules
Manually: put the files in place
.claude/commands/configure-rules.mdCall it with /configure-rules. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/configure-rules.mdCall it with /prompts:configure-rules. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/configure-rules.prompt.mdManually: put the files in place
.gemini/commands/configure-rules.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about configure-rules
How do I install configure-rules in Claude Code?
Save the command as .claude/commands/configure-rules.md.
What does configure-rules do?
It guides personalization-rule changes from dependency checks and variant mapping through QA and deployment logging.
Where does configure-rules store its plan?
It saves the plan in .claude/plans/plan-<timestamp>.json, alongside deployment and audit details.
Source text
configure-rules.md · Apache-2.0
--- name: configure-rules description: Deploys decision logic, content variants, and delivery rules across personalization channels. usage: /personalization-engine:configure-rules --initiative "PLG Onboarding" --environment staging --channels "web,in-app" --- # Command: configure-rules ## Inputs - **initiative** – reference to the personalization effort from `define-profiles`. - **environment** – staging | production to govern deployment steps. - **channels** – comma-separated list of activation surfaces. - **change_type** – net-new, update, rollback. - **approvers** – optional stakeholders for governance sign-off. ### GTM Agents Pattern & Plan Checklist > Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325. - **Pattern selection**: Rule configuration generally runs **pipeline** (pre-flight → decision build → variant mapping → QA → deployment). If decision build + variant prep happen in parallel, note a **diamond** block with merge gate in the plan header. - **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing initiative, environments, dependency graph (data eng, creative, QA, governance), error handling, and success metrics (latency, personalization lift, incident count). - **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for rule diffing, Context7 for platform SOPs, Sequential Thinking for go/no-go reviews, Playwright for simulation/QA evidence capture. - **Guardrails**: Default retry limit = 2 for deployment/QA failures; escalation ladder = Personalization Architect → Data Privacy Lead → Exec sponsor. - **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before deployment to confirm dependencies + approvals. ## Workflow 1. **Pre-flight Review** – validate profiles, data freshness, consent status, and experiment dependencies. 2. **Decision Flow Build** – configure rules, weights, or model endpoints in MAP/CDP/product tooling. 3. **Variant Mapping** – link each rule outcome to content assets, CTAs, and fallback experiences. 4. **QA & Simulation** – run synthetic traffic through decision trees, capture screenshots/logs. 5. **Deployment & Logging** – push changes via API/CLI, note version metadata, set up monitoring hooks. ## Outputs - Deployment runbook with rule IDs, version numbers, and rollback plan. - QA evidence (simulation results, screenshots, payload logs). - Governance log including approvers, timestamps, and linked experiments. - Plan JSON entry stored/updated in `.claude/plans` for audit trail. ## Agent/Skill Invocations - `customer-data-engineer` – ensures data pipelines and environments are ready. - `personalization-architect` – verifies experience logic + content mapping. - `content-variants` skill – tracks asset requirements + approvals. - `governance` skill – enforces change controls and compliance steps. ## GTM Agents Safeguards - **Fallback agents**: document substitutes (e.g., governance lead covering architect) when owners unavailable. - **Escalation triggers**: if QA fails twice, latency spikes, or privacy gate blocks deployment, trigger GTM Agents rip-cord and log remediation in plan JSON. - **Plan maintenance**: update plan JSON/change log when rule sets, environments, or deployment windows change so reviewers can trace history. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents