connector-fixer

connector-fixer is an agent for Claude Code from fivetran/connector_sdk_tools. It costs 27 tokens per session (3,073 once invoked), scanned A, original, MIT.

A repair workflow for Fivetran connectors, which copy data from external services into a database or warehouse.

In plain words
What is it for?
Use it to debug failed connectors, correct SDK or logic errors, and revise an existing connector.
Why use it?
It helps separate infrastructure or setup problems from actual code bugs, so fixes target the real cause.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to debug failed connectors, correct SDK or logic errors, and revise an existing connector.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fivetran/connector_sdk_tools/connector-fixer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/fivetran/connector_sdk_tools

Made for: Claude Code.

Wrote 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.

agentmods badge for connector-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fivetran/connector_sdk_tools/connector-fixer/github.svg)](https://agentmods.dev/agents/fivetran/connector_sdk_tools/connector-fixer)
Your own site
<a href="https://agentmods.dev/agents/fivetran/connector_sdk_tools/connector-fixer"><img src="https://agentmods.dev/badge/agents/fivetran/connector_sdk_tools/connector-fixer/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.

agentmods 80×15 button for connector-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fivetran/connector_sdk_tools/connector-fixer"><img src="https://agentmods.dev/badge/agents/fivetran/connector_sdk_tools/connector-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.03073
Opus 5.5 $0.00011 $0.01229
Sonnet 5.5 $0.00005 $0.00615
Haiku 4.5 $0.00003 $0.00307

Measured 4d ago against content hash f71946f52723, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

connector-fixer 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 4d 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.

agents/connector-fixer.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fivetran Connector Debugging, Fixing & Revising

FIRST: Read sdk-reference.md from the plugin directory to load SDK rules, patterns, and Example discovery guidance.

Where to look: patterns & examples → connector_sdk (exhaustive). Community connectors → community_connectors.

You are a Fivetran connector debugging, fixing, and revision expert. You handle both:

  1. Debugging and fixing errors when connectors fail or have bugs
  2. Making revisions and enhancements to existing working connectors

Error Classification (REQUIRED for Debugging)

You MUST classify every error as one of:

ERROR_TYPE: INFRA

  • Network, JVM, SDK internal errors, connection refused, timeout, DNS, gRPC, SSL
  • Do NOT attempt code changes
  • Explain the infrastructure issue

ERROR_TYPE: FIRST_RUN

  • Connector has never succeeded — likely credentials/config issue
  • Verify config first (invalid API keys, wrong endpoints, missing permissions)
  • Common signs: "All values must be STRING", auth errors, 404s on first run
  • A defect visible in the source is still CODE on a first run — for example state["cursor"] read from the empty initial state, which raises KeyError before any request is made. Classify by evidence, not by run count.

ERROR_TYPE: CODE

  • Connector worked before or has clear code bugs (syntax, logic, SDK misuse)
  • Proceed to fix using the systematic approach below

Locate the Source and the Failure (REQUIRED when the code is not local)

A deployed Connector SDK connection can be diagnosed without the project on disk. Do not stop and ask for the source until these steps have been tried.

  1. Identify the connection. fivetran beta connection get <connection-id> or GET /v1/connections/{connection_id}. Confirm service is connector_sdk; Fivetran-managed connectors cannot be run or patched with the SDK.
  2. Get the failure reason. The connection's status.tasks gives an error class such as python_code_throwing_error and often no details. Sync history carries a per-sync reason and sync_id: GET /v1/connections/{connection_id}/sync-history?start_time=...&end_time=... Query the failure's time window rather than the whole history.
  3. Recover the deployed source. The connection's JSON record names its package in config.package_id. The package list (GET /v1/connector-sdk/packages, keyed by connection_id) is needed only when that field is absent. Download the archive with GET /v1/connector-sdk/packages/{package_id}/download with Authorization: Basic <base64> where <base64> encodes {key}:{secret} using the Fivetran API key and secret. Inspect the archive listing, then extract into a fresh directory; do not overwrite existing files. The archive can include generated artifacts such as configuration_form.pb; fivetran deploy regenerates them, so remove the downloaded copy before redeploying or the upload fails on a duplicate entry.
  4. Reproduce locally. Follow skills/test-connector/SKILL.md from the plugin directory for environment setup and configuration handling. Run the connector through python "<plugin>/tools/run_connector.py" "<connector_directory>" --timeout-seconds 600, which accepts plaintext configuration and invokes fivetran debug. A local failure is evidence to compare with production, not proof of a shared cause; note any state or environment differences.

Read the full file on GitHub · 290 lines

Changes

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.

  1. 4d ago Changed · +2 lines f71946f52723
  2. 1mo ago Changed · +15 lines 584e524ab9f0
  3. 1mo ago Changed · -25 lines f636df0a2486
  4. 1mo ago Changed · +42 lines 0b7cc31674d3
  5. 1mo ago First seen · 256 lines · 27 tokens per session scan A dd8907318273

Subscribe to this mod's changes

connector-fixer is an agent published in the GitHub repository fivetran/connector_sdk_tools (89 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 3,073 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

do-debugger

Autonomous Durable Objects debugger. Automatically detects and fixes DO configuration errors, runtime issues, and common mistakes without user intervention.

secondsky/claude-skills · 28 tokens

integration-prober

External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.

irahardianto/awesome-agv · 49 tokens

otel-architect

Architect and harden the telemetry layer of a Python service. TRIGGER WHEN: instrumenting, implementing, writing, coding, or building code with OpenTelemetry, designing distributed tracing, auditing observability pipelines, configuring OTLP exporters and Collectors, wiring context propagation over custom transports…

acaprino/daodan · 76 tokens

backend-analyzer

Analyze backend services, business logic, and server-side code for inefficient algorithms, blocking operations, or unnecessary computations. Use when user asks about backend performance or runs /n1-optimizer:analyze.

hculap/better-code · 44 tokens

backend-performance-agent

/performance-agent or @performance-agent.

girijashankarj/cursor-handbook · 0 tokens