Data Formulator is an interactive workspace where AI agents connect to data sources, answer questions, and create visualizations. It is used to explore and analyze data while branching into related questions without losing the context of each investigative path.
Borrowing it
Nothing to install: this file belongs to microsoft/data-formulator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/data-formulator/main/.cursor/skills/error-handling/SKILL.mdgit clone --depth 1 https://github.com/microsoft/data-formulatorWrote 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/microsoft/data-formulator/error-handling)<a href="https://agentmods.dev/skills/microsoft/data-formulator/error-handling"><img src="https://agentmods.dev/badge/skills/microsoft/data-formulator/error-handling/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/microsoft/data-formulator/error-handling"><img src="https://agentmods.dev/badge/skills/microsoft/data-formulator/error-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk fail
- NVIDIA SkillSpector pass
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 | $0.00034 | $0.03637 |
| Opus 5.5 | $0.00014 | $0.01455 |
| Sonnet 5.5 | $0.00007 | $0.00727 |
| Haiku 4.5 | $0.00003 | $0.00364 |
Grade A, and why
error-handling 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 1mo 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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Handling Skill
Unified error handling system for DF. Use when adding API endpoints, modifying error handling, or adding frontend API calls.
Prerequisites: Read
docs/dev-guides/7-unified-error-handling.mdbefore changing API error behavior. Readdocs/dev-guides/2-log-sanitization.mdwhen the work involves logging, credentials, external services, or DataLoaders. If your work introduces new error handling patterns or conventions, update this file and related dev-guides accordingly.
Architecture Overview
Frontend Backend
──────── ───────
apiClient.ts errors.py
├── apiRequest() ←── JSON ──── ├── ErrorCode (enum)
├── streamRequest() ←── NDJSON ── └── AppError (exception)
└── parseStreamLine()
error_handler.py
errorCodes.ts ├── register_error_handlers(app)
└── getErrorMessage() ├── classify_and_wrap_llm_error()
└── stream_error_event()
errorHandler.ts
└── handleApiError() security/sanitize.py
└── classify_llm_error() (internal)
MessageSnackbar ← dfSlice.messages
Protocol Snapshot
Use this contract for all new or reworked DF APIs:
| Scenario | HTTP | Shape |
|---|---|---|
| Non-streaming success | 200 |
{"status": "success", "data": ...} |
| Non-streaming business/validation error | 200 |
{"status": "error", "error": {"code", "message", "retry", "request_id"}} |
| Non-streaming auth/authorization error | 401 / 403 |
same structured error body |
| Streaming preflight error | 200 |
application/json + {"status": "error", "error": ...} |
| Streaming in-flight fatal error | 200 |
NDJSON line: {"type": "error", "error": ...} |
| No Flask route / too large / unhandled crash | 404 / 413 / 500 |
transport-level error |
Do not use HTTP 400/422 for application validation errors in new code.
Do not convert in-flight NDJSON errors to status: "error"; once the stream has
started, event type is the protocol discriminator.
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.
- 1mo ago First seen · 382 lines · 34 tokens per session scan A 760917e7d8c8
error-handling is a skill published in the GitHub repository microsoft/data-formulator (17,584 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 3,637 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.
Other skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
platform-apex-anonymous-run
Runs anonymous Apex against the connected org (.apex file or pasted snippet), capturing the debug log, surfacing errors. Triggers on "run this anonymous apex", "execute this script against my org", "what does this code return", or "execute scripts/foo.apex". Wraps scripts in savepoint+rollback; warns before running in…