flow-codeblock

Instructions for using Flow Codeblock MCP tools to write JavaScript and manage persistent scripts, including validation, publishing, execution, and ownership actions.

In plain words
What is it for?
Use them when creating or changing Flow Codeblock scripts, running them, checking their status, publishing them, or managing ownership.
Why use it?
They define how the agent should route tasks, handle authentication, and refuse unsupported actions such as script deletion.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/renoelis/flow-codeblock-mcp/flow-codeblock
Any agent
npx skills add renoelis/flow-codeblock-mcp --skill flow-codeblock
Clone the repo
git clone --depth 1 https://github.com/renoelis/flow-codeblock-mcp

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00991
Opus 5 $0.00026 $0.00495
Sonnet 5 $0.00010 $0.00198
Haiku 4.5 $0.00005 $0.00099

Measured yesterday against content hash 89704c631b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flow-codeblock 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 yesterday.

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.

skills/flow-codeblock/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Codeblock

This Skill works with the bundled stdio MCP server. The server calls only the Flow Codeblock Rust API; user JavaScript always runs in the server-side Bun Supervisor.

Boundaries

  • The MCP server requires FLOW_CODEBLOCK_BASE_URL and FLOW_CODEBLOCK_TOKEN; optional FLOW_CODEBLOCK_OWNER_EMAIL and FLOW_CODEBLOCK_OWNER_NAME provide defaults for ownership tools. Explicit tool arguments take precedence.
  • Non-script execution uses FLOW_CODEBLOCK_BASE_URL/flow/codeblock. Script create, update, and execution use the returned script_url at FLOW_CODEBLOCK_BASE_URL/flow/codeblock/{script_id}. Do not ask for a domain or put platform tokens in inputs, code, or documents.
  • MCP provides no script deletion, token-management, or arbitrary HTTP-proxy tool. Refuse deletion requests and direct the user to the Flow Codeblock web UI or REST API.
  • Execution uses the MCP Web worker lane and still applies authentication, quota, rate limiting, security checks, auditing, and statistics.
  • Lock, unlock, release, and transfer ownership only through their dedicated verification-code tools. Never guess, record, or reuse a code.

Tool routing

For any code-writing or interface implementation request, call flow_write_code first and select non_script or script.

  • non_script generates JavaScript for immediate execution and does not create a persistent script. Use flow_execute_code only when the user explicitly requests a test or execution.
  • script generates JavaScript and a complete script-interface-doc.v1 document internally for creates or interface-contract changes. For code-only updates, preserve the current document and do not regenerate it. Do not show either in the final response unless the user asks for them.
  • Read the current script with flow_get_script and only script_id; the server uses version=0. Read a historical version only with an explicit version from the user or available_versions.
  • Read current and historical interface documents with their matching documentation tools when changing or confirming documentation. Do not guess versions.

Read the full file on GitHub · 47 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 47 lines · 51 tokens per session scan A 89704c631b39

Subscribe to this mod's changes

flow-codeblock is a skill published in the GitHub repository renoelis/flow-codeblock-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 991 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens