sandwalk-dev-loop SKILL.md skillB

sandwalk-dev-loop from fastfold-ai/sandwalk is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add fastfold-ai/sandwalk/sandwalk-dev-loop@git:20260929.2f2db49

Pins git:20260929.2f2db49 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
fastfold-ai/sandwalk
Path
.cursor/skills/sandwalk-dev-loop/SKILL.md
Versions recorded
2
Latest version
git:20260929.2f2db49, committed Sep 29, 2026
First version recorded
Sep 29, 2026
Size
4,479 bytes
Repository stars
20
License
Apache-2.0

Run Sandwalk locally from this checkout for development: start the agent API (cli/) on :8787, the dashboard UI (Vite / Tauri) on :1420, stop the packaged Sandwalk.app that holds the same port, and know what hot-reloads vs. what needs a restart. Use when asked to run, restart, or debug the app in dev mode, when a port is busy, or when UI/Python changes are not showing up.

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

# Sandwalk dev loop

Two processes, two terminals. The UI never spawns the API.

| Process | Command | Port | Reloads on edit? |
|---------|---------|------|------------------|
| Agent API (`cli/`) | `scripts/dev-api.sh` | 8787 | **No** — Ctrl+C and re-run after editing `cli/src` |
| Dashboard UI | `scripts/dev-ui.sh` (Tauri window) or `scripts/dev-ui.sh web` (browser) | 1420 | TS/React: HMR. Rust in `src-tauri/`: auto rebuild + relaunch |

## Start

```bash
scripts/stop-packaged-app.sh   # only if Sandwalk.app / the menubar server is running (it owns :8787)
scripts/dev-api.sh             # terminal 1
scripts/dev-ui.sh              # terminal 2 (add `web` for browser-only)
curl -fsS http://127.0.0.1:8787/v1/health      # API up?
```

Run long-lived processes in the background and read their output files; do not
block on them. The API prints `Bench runtime started` when ready; the Tauri dev
prints `Finished \`dev\` profile` then `Running …/sandwalk-desktop`.

## Put something on screen

```bash
node scripts/dev-grid.mjs 4x4                          # 16 fresh chats in a 4×4 split, one prompt each
node scripts/dev-grid.mjs 2x3 --quiet                  # grid only, no messages
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add fastfold-ai/sandwalk/sandwalk-dev-loop@sha256:055c826848959066

The line at the top of this page pins the label git:20260929.2f2db49, 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_s74pxgmuaffud7n3.svg)](https://markdownregistry.com/a/art_s74pxgmuaffud7n3)

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

Versions

The registry has recorded 2 versions of this file, all committed on Sep 29, 2026.

versioncommittedcommitsizeaudit
git:20260929.2f2db49 latest2026-09-29 2f2db49 4,479 BB view · diff
git:20260929.22df6e72026-09-29 22df6e7 3,557 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:8787)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4479 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 script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

fastfold-ai/sandwalk · 20 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_s74pxgmuaffud7n3
GET https://markdownregistry.com/api/v1/resolve?ref=fastfold-ai/sandwalk/sandwalk-dev-loop
GET https://markdownregistry.com/api/v1/blob/055c826848959066c45814917d62ad86595d4939b7e4e079b6241483b5b903b1

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 fastfold-ai/sandwalk

sandwalk-testing SKILL.md skill
fastfold-ai/sandwalk · .cursor/skills/sandwalk-testing/SKILL.md · Test and benchmark Sandwalk changes the way CI does: which checks to run per change type (web unit + coverage gate, CLI…
git:20260929.6902891 · audit A · 20 stars
AGENTS.md AGENTS.md file
fastfold-ai/sandwalk · AGENTS.md
git:20260929.22df6e7 · audit A · 20 stars
CLAUDE.md@cli CLAUDE.md file
fastfold-ai/sandwalk · cli/CLAUDE.md
git:20260812.d0afc1a · audit A · 20 stars
knowledge-steward SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/knowledge_steward/SKILL.md · Curate Sandwalk's persistent Memory (USER.md, MEMORY.md, Specialist PRIORS.md), Living Markdown Wiki ([[wikilinks]])…
v1.0.0 · audit A · 20 stars
omnigraph SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/omnigraph/SKILL.md · Operate Sandwalk's local Omnigraph engine and runnable Cookbook Modes (Biomed Research, Pharma Intel, Industry Intel…
v1.0.0 · audit A · 20 stars
sites-building SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/sites_building/SKILL.md · Build, preview, validate, and prepare static websites, HTML reports, dashboards, landing pages, and Vite/React sites…
v1.2.1 · audit A · 20 stars
sites-hosting SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/sites_hosting/SKILL.md · Securely package and publish a validated static dist directory to Sandwalk Sites, then wait for a ready public URL.
v1.0.0 · audit A · 20 stars
skill-creator SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/skill_creator/SKILL.md · Create new agent skills and iteratively improve them. Use when the user wants to build, scaffold, author, validate…
v1.0.0 · audit A · 20 stars
skill-find SKILL.md skill
fastfold-ai/sandwalk · cli/src/skills/skill_find/SKILL.md · Discover, try without installing, and install agent skills — first from the official Fastfold catalog…
v1.0.0 · audit A · 20 stars

Every file in fastfold-ai/sandwalk

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