run-waterfall-enrichment — Claude Code command: install
The run-waterfall-enrichment command for Claude Code enriches contacts or companies through providers with a credit cap. It routes the results to a CRM, CSV, or warehouse.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/run-waterfall-enrichment.mdWhat run-waterfall-enrichment does
The command checks the input, filters out records from recent runs, and applies rate limits. It selects providers from the configured order or a sequence supplied for the run, then calls them in turn. You can set the record type, input payload, and maximum credit spend.
Next, it combines the returned data, adds confidence and provenance details, and sends the result to a CRM, CSV, or warehouse. Reports track credits and latency; alerts are recorded when providers fail or the credit ceiling is reached. A low ceiling can stop the run before the provider sequence returns the data you need.
What it helps with
- enrich a contact or company with provider data
- choose the order in which providers are queried
- cap credit use for an enrichment run
- send results to a CRM, CSV, or warehouse
- log provider failures and credit-limit alerts
Example prompts for the agent
- Enrich Taylor Reed at Nimbus through Apollo, Hunter, and RocketReach with a five-credit cap:
/data-signal-enrichment:run-waterfall-enrichment --type contact --input "Taylor Reed, Nimbus" --sequence apollo,hunter,rocketreach --max-credits 5. - Enrich the company for
nimbus.exampleand send the result to the CRM:/data-signal-enrichment:run-waterfall-enrichment --type company --input "nimbus.example" --delivery crm. - Check the technology stack for
nimbus.exampleand deliver the result as CSV:/data-signal-enrichment:run-waterfall-enrichment --type technographic --input "nimbus.example" --delivery csv.
How to install run-waterfall-enrichment
Manually: put the files in place
.claude/commands/run-waterfall-enrichment.mdCall it with /run-waterfall-enrichment. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/run-waterfall-enrichment.mdCall it with /prompts:run-waterfall-enrichment. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/run-waterfall-enrichment.prompt.mdManually: put the files in place
.gemini/commands/run-waterfall-enrichment.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about run-waterfall-enrichment
How do I install run-waterfall-enrichment in Claude Code?
Add the command file at .claude/commands/run-waterfall-enrichment.md.
What does run-waterfall-enrichment do?
It queries data providers in sequence, combines their results, and sends the output to a chosen destination. It also tracks credit use and records failures.
Which data types can run-waterfall-enrichment process?
The command accepts contact, company, technographic, and intent types. You can supply the provider order or use the order from configuration.
Source text
run-waterfall-enrichment.md · Apache-2.0
--- name: run-waterfall-enrichment description: Executes provider waterfalls with credit governance, failover rules, and delivery targets. usage: /data-signal-enrichment:run-waterfall-enrichment --type contact --input "Taylor Reed, Nimbus" --sequence apollo,hunter,rocketreach --max-credits 5 --- # Command: run-waterfall-enrichment ## Inputs - **type** – contact | company | technographic | intent. - **input** – record payload (name/company/email/domain/file). - **sequence** – optional ordered provider list; default uses ops config. - **max-credits** – ceiling for total credits to consume. - **delivery** – crm | csv | warehouse specifying output target. ## Workflow 1. **Request Validation** – confirm fields, dedupe against recent runs, and enforce rate limits. 2. **Sequence Selection** – pull provider order from configs, adjust for overrides or outages. 3. **Execution Loop** – call providers, capture response metadata, apply validation logic. 4. **Aggregation & Scoring** – merge best data, attach confidence + provenance tags. 5. **Delivery & Logging** – push to destination, log credits, update success dashboards, trigger alerts if thresholds exceeded. ## Outputs - Enrichment payload (JSON/CSV/CRM payload) with fields, provider, timestamp, confidence. - Credit + latency report appended to provider utilization table. - Alert entries when max-credits hit or providers fail. ## Agent/Skill Invocations - `provider-ops-lead` – supplies sequence + credit policy. - `signal-integrator` – handles normalization + delivery. - `data-quality-steward` – validates results before release. - `waterfall-blueprint` skill – enforces sequencing template. - `provider-scorecard` skill – logs performance + cost metrics. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents