bean SKILL.md skillA

bean from grainulation/grainulator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add grainulation/grainulator/bean@git:20260908.608fac0

Pins git:20260908.608fac0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
grainulation/grainulator
Path
packages/runtime/skills/bean/SKILL.md
Versions recorded
1
Latest version
git:20260908.608fac0, committed Sep 8, 2026
Size
6,984 bytes
Repository stars
86
License
MIT

Run a task as a recursive convergence loop, not a fixed checklist: investigate the most decisive open question, record what you learn as typed evidence in a ledger, let a compiler score what is still weak or contradictory, revise beliefs that new evidence overturns, and loop until the evidence converges — then deliver. Continuously spins up subagents and uses whatever skills/connectors exist. Verbose by default. Trigger on /bean, on "do this thoroughly / be systematic / deep work mode", OR…

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

# bean

bean runs a task the way the Fable model worked: it keeps looking where a one-shot answer
would stop, kills its own incorrect beliefs as it learns, validates its work against a
real signal before declaring done, and improves from its own accumulated notes. It is a
**recursive convergence loop**, not a fixed sequence of phases.

bean runs on a **runtime**: a _claim ledger_ (typed evidence with tiers, that can be
superseded) plus a _compiler_ that scores convergence (conflicts, coverage gaps, weak
evidence, undischarged risks) and **exits nonzero until it is reached**. bean ships its own
self-contained compiler — `bean-check`, a single static binary — as the default, so the loop
has a real gate that runs anywhere. In strict mode it gates load-bearing claims on a real
external oracle (`verified_by` + `bean-verify`), and a native Stop hook (`bean-hook`) couples
it to execution so the agent can't finish until it converges. **grainulator/wheat** is an
optional richer backend when present. See [references/runtime.md](references/runtime.md).

**A note on what this is.** bean shapes the _procedure_ a model follows, not its
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add grainulation/grainulator/bean@sha256:1cdded1e6618ccd7

The line at the top of this page pins the label git:20260908.608fac0, 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_ssgqbi4lqeze56pm.svg)](https://markdownregistry.com/a/art_ssgqbi4lqeze56pm)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 8, 2026.

versioncommittedcommitsizeaudit
git:20260908.608fac0 latest2026-09-08 608fac0 6,984 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 (6984 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

grainulation/grainulator · 86 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ssgqbi4lqeze56pm
GET https://markdownregistry.com/api/v1/resolve?ref=grainulation/grainulator/bean
GET https://markdownregistry.com/api/v1/blob/1cdded1e6618ccd7665e36749ab2b8542fcdfa072e732265e17bf0366bfb1e4b

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 grainulation/grainulator

AGENTS.md AGENTS.md file
grainulation/grainulator · AGENTS.md
git:20261103.2b1463d · audit A · 86 stars
AGENTS.md@packages/evidence AGENTS.md file
grainulation/grainulator · packages/evidence/AGENTS.md
git:20260908.608fac0 · audit A · 86 stars
analytics SKILL.md skill
grainulation/grainulator · skills/analytics/SKILL.md · Sprint analytics — type distributions, stale claims, velocity, prediction scoring
git:20260922.e702f49 · audit A · 86 stars
blind-spot SKILL.md skill
grainulation/grainulator · skills/blind-spot/SKILL.md · Structural gap analysis -- find what the sprint has not considered.
git:20260922.e702f49 · audit A · 86 stars
brief SKILL.md skill
grainulation/grainulator · skills/brief/SKILL.md · Generate a compiled decision brief from the current sprint's claims.
git:20260922.e702f49 · audit A · 86 stars
calibrate SKILL.md skill
grainulation/grainulator · skills/calibrate/SKILL.md · Score past predictions against actual outcomes. Closes the feedback loop.
git:20260922.e702f49 · audit A · 86 stars
challenge SKILL.md skill
grainulation/grainulator · skills/challenge/SKILL.md · Adversarial testing of a specific claim. Try to disprove it.
git:20261025.4ee95a6 · audit A · 86 stars
feedback SKILL.md skill
grainulation/grainulator · skills/feedback/SKILL.md · Record stakeholder input — new constraints, corrections, or direction changes.
git:20260922.e702f49 · audit A · 86 stars
fetch SKILL.md skill
grainulation/grainulator · skills/fetch/SKILL.md · Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw…
git:20260922.e702f49 · audit A · 86 stars
grainulator SKILL.md skill
grainulation/grainulator · skills/grainulator/SKILL.md · Use Grainulator to carry a substantial research or engineering task through investigation, implementation, and…
git:20260922.e702f49 · audit A · 86 stars
healthcheck SKILL.md skill
grainulation/grainulator · skills/healthcheck/SKILL.md · Check the unified Grainulator MCP server and local CLI without blocking useful work on optional connectors.
git:20260922.e702f49 · audit A · 86 stars
init SKILL.md skill
grainulation/grainulator · skills/init/SKILL.md · Initialize a dedicated sprint using the unified tool or local CLI while preserving existing data.
git:20260922.e702f49 · audit A · 86 stars

Every file in grainulation/grainulator

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