decide SKILL.md skillA

decide from blockrunai/blockrun-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add blockrunai/blockrun-mcp/decide@git:20261011.5cc7b5e

Pins git:20261011.5cc7b5e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
blockrunai/blockrun-mcp
Path
skills/decide/SKILL.md
Versions recorded
2
Latest version
git:20261011.5cc7b5e, committed Oct 11, 2026
First version recorded
Sep 20, 2026
Size
8,243 bytes
Repository stars
391
License
MIT

Use when the user wants typed judgments over their own data from Claude Code — yes/no probabilities, a labelled choice, or a rubric score over text or images, many items at a time. BlockRun's Decisions endpoint (OpenAI Decisions-compatible, gpt-6-luna): served only at POST api.blockrun.ai/v1/decisions, free with a BlockRun key (no x402 rail). Not an MCP tool: call it with curl. Replaces the OpenJev-backed /v1/decide, which is retired.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Decisions — typed judgments from Claude Code

`POST https://api.blockrun.ai/v1/decisions` takes an **input** (a message, a ticket,
a diff, a tool result, an image) and a list of **questions** with a fixed answer
space, and returns one typed answer per question — no prose to parse. It is
compatible with OpenAI's Decisions API and served by `gpt-6-luna`.

It is **not a BlockRun MCP tool**, on purpose: you are already a frontier model,
and for a one-off "is this urgent?" you are the better judge. The endpoint earns
its place when the user wants the *same fixed ruler over many items*, or is
prototyping a judgment they will later run from a pipeline **without** a model.
From Claude Code, call it with `curl` from the shell.

## Where to call it

| Endpoint | Auth | Price |
|---|---|---|
| `https://api.blockrun.ai/v1/decisions` | `Authorization: Bearer brk_live_…` | Free for any registered key, per-key hourly limit |

That is the only rail. Decisions is **not sold over x402**: the x402 per-call
floor is above what a Decisions call costs, so a paid route would bill nearly
every call at the floor. Do not look for it on `blockrun.ai` or
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add blockrunai/blockrun-mcp/decide@sha256:73c287cb0db9be95

The line at the top of this page pins the label git:20261011.5cc7b5e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_62affshqdpqvff2d.svg)](https://markdownregistry.com/a/art_62affshqdpqvff2d)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 20, 2026 and Oct 11, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
git:20261011.5cc7b5e latest2026-10-11 5cc7b5e 8,243 BA view · diff
git:20260920.cdfe8312026-09-20 cdfe831 9,910 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8243 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

blockrunai/blockrun-mcp · 391 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_62affshqdpqvff2d
GET https://markdownregistry.com/api/v1/resolve?ref=blockrunai/blockrun-mcp/decide
GET https://markdownregistry.com/api/v1/blob/73c287cb0db9be953492cfa01e96ef4fc62e38e0d14f14c468956cc97f111ef1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from blockrunai/blockrun-mcp

AGENTS.md AGENTS.md file
blockrunai/blockrun-mcp · AGENTS.md
git:20260915.f9480ad · audit A · 391 stars
CLAUDE.md CLAUDE.md file
blockrunai/blockrun-mcp · CLAUDE.md
git:20260915.f9480ad · audit A · 391 stars
blockrun-debug SKILL.md skill
blockrunai/blockrun-mcp · skills/blockrun-debug/SKILL.md · Use when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT…
git:20260915.c39cc81 · audit B · 391 stars
blockrun-setup SKILL.md skill
blockrunai/blockrun-mcp · skills/blockrun-setup/SKILL.md · Use when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude…
git:20260920.cdfe831 · audit A · 391 stars
blockrun-upgrade SKILL.md skill
blockrunai/blockrun-mcp · skills/blockrun-upgrade/SKILL.md · Use when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a…
git:20260830.d848115 · audit B · 391 stars
blockrun SKILL.md skill
blockrunai/blockrun-mcp · skills/blockrun/SKILL.md · Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on…
v1 · audit A · 391 stars
crypto-data SKILL.md skill
blockrunai/blockrun-mcp · skills/crypto-data/SKILL.md · Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity…
git:20260909.c091b8d · audit A · 391 stars
exa-research SKILL.md skill
blockrunai/blockrun-mcp · skills/exa-research/SKILL.md · Use when researching products, finding academic papers, discovering competitors, reading webpage content, or getting…
git:20260808.b00dcdb · audit A · 391 stars
gentech-blockrun SKILL.md skill
blockrunai/blockrun-mcp · skills/gentech-blockrun/SKILL.md · GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized…
git:20261020.af250db · audit A · 391 stars
image-prompting SKILL.md skill
blockrunai/blockrun-mcp · skills/image-prompting/SKILL.md · Use when generating or editing images via `blockrun_image` — especially with GPT Image 2, Nano Banana, or Grok Imagine…
git:20261020.af250db · audit A · 391 stars
modal SKILL.md skill
blockrunai/blockrun-mcp · skills/modal/SKILL.md · Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a…
git:20260905.a5f248d · audit A · 391 stars
phone SKILL.md skill
blockrunai/blockrun-mcp · skills/phone/SKILL.md · Use when the user wants phone-number intelligence (lookup, carrier, line type, SIM-swap / call-forwarding fraud…
git:20260909.c091b8d · audit A · 391 stars

Every file in blockrunai/blockrun-mcp

Other files named decide

decide SKILL.md skill
alirezarezvani/claude-skills · .gemini/skills/decide/SKILL.md
git:20260821.7405298 · audit C · 28,445 stars
decide SKILL.md skill
outlinedriven/outline-driven-development · .devin/skills/decide/SKILL.md · Use when the user has a fork and wants it resolved and applied, not explored: "decide this", "choose the path", or…
git:20260905.1f63894 · audit A · 53 stars
decide SKILL.md skill
wrg32786/aigent-os · skills/decide/SKILL.md · Run a decision through the 12-lens framework
git:20260707.2a2e857 · audit A · 24 stars
decide SKILL.md skill
arcticfox2029/chamnan · skills/decide/SKILL.md · A reusable decision procedure, and a copyable prototype for the guard that encodes it — derive the population, set one…
git:20260922.3c3a804 · audit B · 10 stars
decide SKILL.md skill
aiyo28/memento-os · adapters/codex/skills/decide/SKILL.md · Composable decision skill. Core OODA loop: present options, assess confidence, record reasoning artifact with priority…
v2.0.0 · audit A · 4 stars
decide SKILL.md skill
martineserios/thebrana · system/skills/decide/SKILL.md · Decision support — criteria, scenarios, patterns, recommendation.
git:20260812.579b97d · audit A · 3 stars

Browse by kind, by grade A, or by owner.