Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fivetran/connector_sdk_toolsnpx agentmods add skills/fivetran/connector_sdk_tools/connector-sdk-submitWrote 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/fivetran/connector_sdk_tools/connector-sdk-submit)<a href="https://agentmods.dev/skills/fivetran/connector_sdk_tools/connector-sdk-submit"><img src="https://agentmods.dev/badge/skills/fivetran/connector_sdk_tools/connector-sdk-submit/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/fivetran/connector_sdk_tools/connector-sdk-submit"><img src="https://agentmods.dev/badge/skills/fivetran/connector_sdk_tools/connector-sdk-submit.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 | $0.00045 | $0.03123 |
| Opus 5.5 | $0.00018 | $0.01249 |
| Sonnet 5.5 | $0.00009 | $0.00625 |
| Haiku 4.5 | $0.00005 | $0.00312 |
Grade A, and why
connector-sdk-submit 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 today.
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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit Connector SDK Contribution
Use this skill immediately before a contributor opens their first Connector SDK example-connector pull request. Its authority is the selected target repository's GitHub review instructions under .github/instructions. Do not use external examples or generic Python conventions as a substitute.
Establish the scope and authority
- Ask for the connector directory if it was not supplied. Identify the enclosing Git repository.
- Choose the PR destination using these repository rules:
- Use
fivetran/community_connectorsfor a new, standalone connector for a specific source; or a focused bug fix, reliability/performance improvement, or documentation update to an existing Community Connector. New connectors belong in a top-level connector directory and must be listed in that repository's rootREADME.md. - Use
fivetran/connector_sdkfor a Connector SDK template, quickstart/tutorial, reusable generic SDK pattern. Place examples in the repository's existingexamples/. - If the work could be treated as either a reusable SDK example/pattern or a standalone source connector, prioritize
fivetran/community_connectors. Submit the standalone connector there; do not split the work or create PRs in both repositories. - If the files already belong to one repository, keep the PR in that repository.
- Use
- State the selected repository and the rule that led to the decision. If none of the rules applies, ask the contributor to choose; do not guess.
- Before reviewing or editing, read these instruction files from the selected target repository—either
fivetran/community_connectorsorfivetran/connector_sdk:.github/instructions/configuration-review.instructions.md.github/instructions/python-review.instructions.md.github/instructions/readme-markdown.instructions.mdIf the contribution is in the selected repository, use its local files. Otherwise, ask the contributor for a checkout path for that repository.
- If the selected target repository or its instruction checkout is unavailable, explain the missing item in plain language and offer to obtain it. For example: “I need a local checkout of the selected repository to apply its submission rules. May I clone the upstream repository, or would you prefer to fork it first?” Wait for approval before cloning, forking, authenticating, or changing remotes.
- Confirm that the target is a connector/example directory containing
connector.py. If it is not, stop and explain that this skill supports connector/example submissions only; do not apply it to documentation-only, tooling, or repository-maintenance changes. - Inspect the connector's changed files and its relevant files:
connector.py,README.md, and dependency files, excluding configuration contents and raw configuration diffs. Discover configuration-like files by path only at this stage; defer reading their contents until the submission configuration has been selected and can be scanned locally without exposing values, as described below. Do not inspect or print real local configuration files such asconfiguration_local.json.
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.
- today First seen · 177 lines · 45 tokens per session scan A 9324ce579398
connector-sdk-submit is a skill published in the GitHub repository fivetran/connector_sdk_tools (89 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 3,123 once invoked, about $0.0002 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 2026-10-29.
Other skills, from other repositories
esp32-arch-review
Reviews ESP32 firmware architecture for FreeRTOS safety, memory and stack sizing, ISR rules, error handling, peripheral and pin safety, networking, storage, logging and build configuration, and returns a PASS / PASS WITH NOTES / FAIL report. Use when the user asks to "review the architecture", "code review this…
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
kicad-pcb-review
KiCad PCB review and manufacturing readiness agent skill for Cursor.
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
vllm-rocm-pr-review
Review AMD/ROCm-related pull requests from the vllm-project/vllm GitHub repository and produce a single combined Chinese report: a detailed PR summary (summary, background & motivation, code-change analysis with Mermaid diagrams, technical principles, discussion highlights, risk table) followed by severity-sorted…
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.