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 agentmods add skills/prefecthq/prefect-mcp-server/workflowsnpx skills add PrefectHQ/prefect-mcp-server --skill workflowsgit clone --depth 1 https://github.com/PrefectHQ/prefect-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/prefecthq/prefect-mcp-server/workflows)<a href="https://agentmods.dev/skills/prefecthq/prefect-mcp-server/workflows"><img src="https://agentmods.dev/badge/skills/prefecthq/prefect-mcp-server/workflows.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00657 |
| Opus 5 | $0.00026 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
workflows 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prefect Workflows
Use the Prefect MCP tools as the canonical source for Prefect state, documentation, and release notes. They return structured data with complete identifiers and are read-only unless a tool explicitly says otherwise.
Choose a Workspace
The hosted MCP server authenticates with Prefect Cloud OAuth. If a tool needs a
workspace_id and the user has not selected one:
- Call
list_authorized_workspaces. - Use the only workspace automatically when exactly one is available.
- When several are available, choose from explicit conversation context or ask the user which workspace they mean.
- Pass the selected
workspace_idconsistently to subsequent tool calls.
Never guess a workspace ID or copy one from an unrelated result.
Diagnose Operational Problems
Start broad and narrow only as needed:
- Use
get_dashboardfor an overview of recent failures, lateness, deployments, and work-pool health. - Use
get_flow_runsto inspect the affected run and preserve its full UUID. - Use
get_deployments,get_work_pools,get_task_runs, orread_eventsfor the specific layer implicated by the run. - Explain the evidence, distinguish the observed failure from likely causes, and recommend the smallest next check or action.
Do not repeatedly fetch broad lists when a specific ID is already known.
Documentation and Release Notes
Use the Prefect documentation tools for current CLI, SDK, deployment, and release information. For release questions, search for the current structured release notes and report the exact version and release date returned by the source.
Do not answer version-sensitive questions from memory when the documentation tools are available.
Mutations and the Prefect CLI
The hosted Prefect MCP surface is read-only. Do not claim that it triggered, cancelled, created, updated, or deleted anything unless an exposed tool actually performed that operation.
A local Prefect CLI is a separate, advanced path. Use it only when all of these are true:
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.
- 6d ago First seen · 79 lines · 51 tokens per session scan A 2baec42119d4
workflows is a skill published in the GitHub repository PrefectHQ/prefect-mcp-server (52 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 657 once invoked, about $0.0003 per session on Opus 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
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
bug-triage
Triage open GitHub bug issues for Apify MCP server. Fetches issues, analyzes root causes, drafts developer-to-developer responses, and posts after user approval. Use when handling user bug reports, responding to issues, or cleaning up stale bugs.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
aiox-dev
Full Stack Developer (Dex). Use for code implementation, debugging, refactoring, and development best practices.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - reproduce and isolate before changing anything.
unity-runtime-performance
Use for runtime performance triage from the project filesystem: quality tiers, graphics/URP-HDRP settings, lighting, large assets, scene complexity proxies, and build-size hotspots (no Editor Profiler required).