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/renoelis/flow-codeblock-mcp/flow-codeblocknpx skills add renoelis/flow-codeblock-mcp --skill flow-codeblockgit clone --depth 1 https://github.com/renoelis/flow-codeblock-mcpWhat 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 | $0.00051 | $0.00991 |
| Opus 5 | $0.00026 | $0.00495 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
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.
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_URLandFLOW_CODEBLOCK_TOKEN; optionalFLOW_CODEBLOCK_OWNER_EMAILandFLOW_CODEBLOCK_OWNER_NAMEprovide 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 returnedscript_urlatFLOW_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_scriptgenerates JavaScript for immediate execution and does not create a persistent script. Useflow_execute_codeonly when the user explicitly requests a test or execution.scriptgenerates JavaScript and a completescript-interface-doc.v1document 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_scriptand onlyscript_id; the server usesversion=0. Read a historical version only with an explicit version from the user oravailable_versions. - Read current and historical interface documents with their matching documentation tools when changing or confirming documentation. Do not guess versions.
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.
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.
- yesterday First seen · 47 lines · 51 tokens per session scan A 89704c631b39
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…