swarm-debug SKILL.md skillA

swarm-debug from etr/groundwork is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add etr/groundwork/swarm-debug@git:20260915.8bb3c0a

Pins git:20260915.8bb3c0a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
etr/groundwork
Path
skills/swarm-debug/SKILL.md
Versions recorded
5
Latest version
git:20260915.8bb3c0a, committed Sep 15, 2026
First version recorded
Sep 12, 2026
Size
14,076 bytes
Repository stars
45
License
MIT

Start swarm debugging with parallel hypothesis investigation. Usage /groundwork:swarm-debug [bug description].

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

# Swarm Debugging

## Overview

Parallel adversarial investigation. Multiple teammates test competing hypotheses simultaneously, actively trying to disprove each other. Converges on root cause faster by fighting anchoring bias.

**Core principle:** One investigator anchors on their first theory. A team of investigators who must disprove each other cannot.

This skill extends the `groundwork:debug` workflow. Phases 1-2 and 4-5 follow that skill exactly. Phase 3 (ISOLATE) is replaced by parallel swarm investigation using Claude Code agent teams.

## Pre-flight: Model Recommendation

**Your current effort level is `{{effort_level}}`.**

Skip this step silently if effort is `high`, `xhigh`, or `max` (the scale is `low` < `medium` < `high` < `xhigh` < `max`, so `xhigh` and `max` are already above `high`) AND you are Opus (1M context).
If effort is `low` or `medium` (i.e. below `high`), you MUST show the recommendation prompt — regardless of model.
If you are not Opus (1M context), you MUST show the recommendation prompt - regardless of effort level.

Otherwise → use `AskUserQuestion`:

```json
{
  "questions": [{
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add etr/groundwork/swarm-debug@sha256:058826c8868ed9bd

The line at the top of this page pins the label git:20260915.8bb3c0a, 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_vzeqhllv2yo3dvr4.svg)](https://markdownregistry.com/a/art_vzeqhllv2yo3dvr4)

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

Versions

The registry has recorded 5 versions of this file, between Sep 12, 2026 and Sep 15, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260915.8bb3c0a latest2026-09-15 8bb3c0a 14,076 BA view · diff
git:20260913.04b1d3b2026-09-13 04b1d3b 13,987 BA view · diff
git:20260913.48974952026-09-13 4897495 13,990 BA view · diff
git:20260912.3e89f412026-09-12 3e89f41 13,831 BA view · diff
git:20260912.480a1452026-09-12 480a145 13,530 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 (14076 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

etr/groundwork · 45 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vzeqhllv2yo3dvr4
GET https://markdownregistry.com/api/v1/resolve?ref=etr/groundwork/swarm-debug
GET https://markdownregistry.com/api/v1/blob/058826c8868ed9bdc4337aee2cf1e1c6365ca4da27d83ef0bd4a2d58d4cb2b23

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 etr/groundwork

AGENTS.md AGENTS.md file
etr/groundwork · AGENTS.md
git:20260913.a08ec3f · audit A · 45 stars
CLAUDE.md CLAUDE.md file
etr/groundwork · CLAUDE.md
git:20260913.a08ec3f · audit A · 45 stars
build-unplanned SKILL.md skill
etr/groundwork · skills/build-unplanned/SKILL.md · Build a feature from description with worktree isolation and TDD. Usage /groundwork:build-unplanned "Add user login"
git:20260912.480a145 · audit A · 45 stars
check-specs-alignment SKILL.md skill
etr/groundwork · skills/check-specs-alignment/SKILL.md · Verify alignment between code and specs. Usage /groundwork:check-specs-alignment
git:20260624.e533827 · audit A · 45 stars
create-tasks SKILL.md skill
etr/groundwork · skills/create-tasks/SKILL.md · Generate implementation tasks from architecture document. Usage /groundwork:create-tasks
git:20260716.aaea421 · audit A · 45 stars
debug SKILL.md skill
etr/groundwork · skills/debug/SKILL.md · This skill should be used when investigating bugs, unexpected behavior, test failures, or any code that does not work…
git:20260913.4897495 · audit A · 45 stars
design-architecture SKILL.md skill
etr/groundwork · skills/design-architecture/SKILL.md · This skill should be used when the user asks to design system architecture, make architectural decisions, or translate…
git:20260624.e533827 · audit A · 45 stars
design-it-twice SKILL.md skill
etr/groundwork · skills/design-it-twice/SKILL.md · Use before committing to a non-trivial module, service boundary, or public API - generate 2-3 divergent interface…
git:20260622.3609064 · audit A · 45 stars
design-product SKILL.md skill
etr/groundwork · skills/design-product/SKILL.md · Create detailed product requirements document (PRD) for a feature. Usage /groundwork:design-product
git:20260716.aaea421 · audit A · 45 stars
domain-modeling SKILL.md skill
etr/groundwork · skills/domain-modeling/SKILL.md · Use when designing a product or feature and the project lacks shared, agreed terminology - builds and maintains a pure…
git:20260622.3609064 · audit A · 45 stars
doubt-driven-development SKILL.md skill
etr/groundwork · skills/doubt-driven-development/SKILL.md · Use when building a high-stakes or hard-to-reverse change - schema/data migrations, auth, payments, public API surface…
git:20260912.480a145 · audit A · 45 stars
finalize-task SKILL.md skill
etr/groundwork · skills/finalize-task/SKILL.md · Use when a task worktree has passed validation - manually commits, merges, and cleans up, or prepares runner-owned…
git:20260831.d5366e7 · audit A · 45 stars

Every file in etr/groundwork

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