ops-swarm SKILL.md skillA
ops-swarm from lyther/agent-surface is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lyther/agent-surface/ops-swarm@git:20261018.a646269Pins git:20261018.a646269 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lyther/agent-surface
- Path
skills/ops-swarm/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261018.a646269, committed Oct 18, 2026
- First version recorded
- Sep 3, 2026
- Size
- 23,955 bytes
- Repository stars
- 65
- License
- MIT
Coordinate a bounded evidence-led multi-agent investigation when a question is broad or under-specified, splits into packets that can be evaluated independently, spans several domains, or has competing hypotheses worth comparing adversarially — and when a prior single-agent pass produced weak or contradictory evidence. Not for work one agent can safely do directly, tightly serial steps, tasks whose real cost is running the same tests repeatedly, or shipping and implementation requests, which…
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
## OBJECTIVE **BOUNDED SWARM INVESTIGATION.** Coordinate multiple specialized agents to clarify, research, challenge, verify, and synthesize an ambiguous operational goal. `ops-swarm` is a coordinator skill. It does not treat agent count, provider diversity, voting, or consensus as proof. It turns a broad issue into bounded work packets, assigns an explicit runtime for each packet, runs independent passes where they add value, then returns evidence, unresolved conflicts, verification status, and the smallest safe next action. Use real external/headless agents when they are available and approved. Codex-native subagents are useful for local fan-out, but they are not the whole swarm. For meaningful swarm work, explicitly consider Kilo CLI or Kilo IDE Agent Manager, Droid exec, Ollama Cloud-backed CLI launches, Grok Build, Claude Code headless, Codex exec, OpenCode, Goose, and other installed agents before falling back to only the current model's subagent tool. Keep the swarm lean. The necessary primitives are: 1. A concrete issue contract and authorization boundary. 2. Independent packets with explicit runtime, model, agent/mode, filescope, and success criteria. …
Read the whole file at its exact version.
How to install
mdr add lyther/agent-surface/ops-swarm@sha256:123c0252c613622eThe line at the top of this page pins the label git:20261018.a646269, 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.
[](https://markdownregistry.com/a/art_36acpki2vqzmeu7q)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 3, 2026 and Oct 18, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.a646269 latest | 2026-10-18 | a646269 | 23,955 B | A | view · diff |
| git:20261015.9d0b8cc | 2026-10-15 | 9d0b8cc | 25,660 B | A | view · diff |
| git:20261015.4c84f67 | 2026-10-15 | 4c84f67 | 25,665 B | A | view · diff |
| git:20260914.e01e96a | 2026-09-14 | e01e96a | 25,471 B | A | view · diff |
| git:20260903.57cbad0 | 2026-09-03 | 57cbad0 | 34,198 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (23955 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
lyther/agent-surface · 65 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_36acpki2vqzmeu7q GET https://markdownregistry.com/api/v1/resolve?ref=lyther/agent-surface/ops-swarm GET https://markdownregistry.com/api/v1/blob/123c0252c613622e1b5477f8fd2862bbcbe9026e3ccb19322327ce9daf21068f
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.