loom-daemon Claude Code subagentA

loom-daemon from rjwalters/kicad-tools is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add rjwalters/kicad-tools/.claude/agents/loom-daemon.md@git:20260811.65ccd62

Pins git:20260811.65ccd62 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
rjwalters/kicad-tools
Path
.claude/agents/loom-daemon.md
Versions recorded
5
Latest version
git:20260811.65ccd62, committed Aug 11, 2026
First version recorded
Apr 13, 2026
Size
2,407 bytes
Repository stars
77
License
MIT

Loom Daemon operator - Tier 2 daemon-mode surface that observes the running Rust `loom-daemon` binary via MCP tools and dispatches sweeps for multi-account autonomous batches. Use to monitor and drive the daemon, not to run a work-generation loop.

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

You are the Loom Daemon operator (Tier 2 daemon-mode surface) for this repository.

The `loom-daemon` is a long-lived **Rust binary** that holds the sweep registry, the event bus, and the reaper task in memory and exposes an MCP-level dispatch + monitoring + pub/sub surface. You coordinate it via MCP tools — you do not run a Python daemon loop, maintain a shepherd pool, or spawn shell processes directly.

Follow the complete role definition in `.loom/roles/loom.md` for:
- Daemon detection — probe reachability with `mcp__loom__list_sweeps` (a healthy daemon returns a possibly-empty registry; a dead one fails fast)
- Dispatching work — `mcp__loom__dispatch_sweep` launches a `/loom:sweep <issue>` child with multi-account OAuth token rotation via `spawn-claude.sh`
- Observing state — `mcp__loom__list_sweeps`, `mcp__loom__get_sweep_status`, `mcp__loom__tail_sweep_log`
- Eventing — `mcp__loom__subscribe_to_events` / `mcp__loom__tail_event_bus` over the frozen 6-topic taxonomy
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rjwalters/kicad-tools/.claude/agents/loom-daemon.md@sha256:e975ea540f8d3f33

The line at the top of this page pins the label git:20260811.65ccd62, 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_ym6rat36pjvge7yw.svg)](https://markdownregistry.com/a/art_ym6rat36pjvge7yw)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in rjwalters/kicad-tools/.claude/agents/loom-daemon.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of loom-daemon.md from somewhere else? Ask it: where did my loom-daemon.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Apr 13, 2026 and Aug 11, 2026, about one every 30 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260811.65ccd62 latest2026-08-11 65ccd62 2,407 BA view · diff
git:20260724.99e3dfd2026-07-24 99e3dfd 2,185 BA view · diff
git:20260720.d85df9a2026-07-20 d85df9a 1,703 BA view · diff
git:20260614.0fa983a2026-06-14 0fa983a 1,636 BA view · diff
git:20260413.45cee092026-04-13 45cee09 1,072 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (2407 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

rjwalters/kicad-tools · 77 stars · license MIT · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ym6rat36pjvge7yw
GET https://markdownregistry.com/api/v1/resolve?ref=rjwalters/kicad-tools/.claude/agents/loom-daemon.md
GET https://markdownregistry.com/api/v1/blob/e975ea540f8d3f33e0a7fab648891f8d97bc9dd4ff63085f64512b4f38ea3250

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: which agent file does what.

More from rjwalters/kicad-tools

loom-architect SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-architect/SKILL.md · Identifies improvement opportunities and creates proposals
git:20261014.c9e8426 · audit A · 77 stars
loom-auditor SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-auditor/SKILL.md · Verifies claims made by other agents against runtime reality by building and testing software
git:20261014.c9e8426 · audit A · 77 stars
loom-builder-complexity SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-complexity/SKILL.md · This document covers complexity assessment, issue decomposition, and scope management for the Builder role. For the…
git:20261014.394e76a · audit A · 77 stars
loom-builder-pr SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-pr/SKILL.md · This document covers PR creation, test output handling, and quality requirements for the Builder role. For the core…
git:20261026.79cebff · audit A · 77 stars
loom-builder-worktree SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder-worktree/SKILL.md · This document covers git worktree management for the Builder role. For the core builder workflow, see `builder.md`.
git:20261014.c9e8426 · audit A · 77 stars
loom-builder SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-builder/SKILL.md · Implements issues labeled loom:issue (human-approved work)
git:20261117.d2f58d4 · audit B · 77 stars
loom-cargo-target-isolation SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-cargo-target-isolation/SKILL.md · **Load when**: you are about to run (or just ran) a local `cargo build`/`cargo test`/`cargo run` whose result will…
git:20261012.bf4491e · audit A · 77 stars
loom-champion SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-champion/SKILL.md · Human avatar for final decisions - promotes quality issues to approved status AND auto-merges Judge-approved PRs that…
git:20261101.cb06282 · audit A · 77 stars
loom-ci-refusals-reference SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-ci-refusals-reference/SKILL.md · **Load when**: `loom-daemon forge wait-checks` printed `LOOM-CHECKS-ERROR` naming an HTTP `401`/`403`/`429`, it left a…
git:20261007.6b901b8 · audit A · 77 stars
loom-comment-body-literal-path SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-comment-body-literal-path/SKILL.md · Single canonical copy; role prompts' short pointers refer here.
git:20261010.688914e · audit A · 77 stars
loom-curator-estimate SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-curator-estimate/SKILL.md · For every issue you actually curate or re-curate, write exactly one concrete, standalone comment in the current issue…
git:20261016.bd59834 · audit A · 77 stars
loom-curator-rate-budget SKILL.md skill
rjwalters/kicad-tools · .agents/skills/loom-curator-rate-budget/SKILL.md · Why `curator.md`'s per-issue recipes are REST, and what is still unmeasured.
git:20261005.f192e8f · audit A · 77 stars

Every file in rjwalters/kicad-tools

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