Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add databar-ai/databar-mcp-server --skill databar-waterfallgit clone --depth 1 https://github.com/databar-ai/databar-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/databar-ai/databar-mcp-server/databar-waterfall)<a href="https://agentmods.dev/skills/databar-ai/databar-mcp-server/databar-waterfall"><img src="https://agentmods.dev/badge/skills/databar-ai/databar-mcp-server/databar-waterfall/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/databar-ai/databar-mcp-server/databar-waterfall"><img src="https://agentmods.dev/badge/skills/databar-ai/databar-mcp-server/databar-waterfall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01191 |
| Opus 5.5 | $0.00028 | $0.00476 |
| Sonnet 5.5 | $0.00014 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
databar-waterfall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Databar Waterfall Enrichment
Waterfalls try multiple data providers in sequence until one returns a result. This maximizes the chance of finding the data. For example, an "email finder" waterfall might try Provider A first, and if it fails, try Provider B, then C — stopping as soon as one succeeds.
When to use this vs a regular enrichment
- Waterfall: User wants the highest chance of finding the data and doesn't care which provider returns it. Best for email finding, phone lookups, and contact discovery.
- Regular enrichment (
databar-enrichmentskill): User wants data from a specific provider, or the task only has one relevant provider.
Workflow
-
Identify the user's goal. Common waterfall use cases:
- Finding someone's email address (given name + company)
- Looking up a phone number
- Finding social profiles
- Any task where the user wants to "try everything"
-
Search for available waterfalls. Call
search_waterfallswith a descriptive query (e.g. "email finder", "phone lookup"). -
Pick the best waterfall. Review the results. Check:
identifier— the string you'll pass to run itinput_params— required parametersavailable_enrichmentscount — more providers = higher success rate
-
Determine single vs bulk.
- If the user provides one record: use
run_waterfall - If the user provides multiple records: use
run_bulk_waterfall
- If the user provides one record: use
-
Confirm cost with the user. Waterfall pricing varies by provider. Tell the user the waterfall name and that costs depend on which provider succeeds.
- For bulk: "Running {waterfall_name} on {count} records. Cost depends on which providers succeed."
-
Run the waterfall.
Single record:
run_waterfall({ waterfall_identifier: "email_getter", params: { full_name: "John Smith", company_name: "Google" } })Multiple records:
run_bulk_waterfall({ waterfall_identifier: "email_getter", params_list: [ { full_name: "John Smith", company_name: "Google" }, { full_name: "Jane Doe", company_name: "Microsoft" } ] })
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 115 lines · 70 tokens per session scan A 09ffd8686382
databar-waterfall is a skill published in the GitHub repository databar-ai/databar-mcp-server (5 stars, last pushed 7mo ago), licensed MIT. It adds 70 tokens to every session and 1,191 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
databar-waterfall compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| databar-waterfalldatabar-ai/databar-mcp-server | Skill | 5 | 7mo ago | MIT | A | 70 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |