lattice-swarm

lattice-swarm is a skill for Claude Code from sectersion/lattice. It costs 110 tokens per session (2,703 once invoked), scanned B, original, MIT.

An orchestration guide for testing several AI agents that coordinate through a Lattice server. Lattice is a shared service where agents can register, exchange replies, claim work, and acknowledge messages.

In plain words
What is it for?
Use it to start Lattice in Docker, create test roles and conversation threads, launch worker agents, and verify the outcome.
Why use it?
It provides the setup and checking steps needed to run a multi-agent coordination test. This avoids manually assembling the server, starting workers, and preparing shared work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the lattice plugin — 2 skills shipped together

Good fit Use it to start Lattice in Docker, create test roles and conversation threads, launch worker agents, and verify the outcome.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sectersion/lattice/lattice-swarm
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sectersion/lattice --skill lattice-swarm
Clone the repo
git clone --depth 1 https://github.com/sectersion/lattice

Made for: Claude Code.

Or install lattice, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lattice-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/sectersion/lattice/lattice-swarm/github.svg)](https://agentmods.dev/skills/sectersion/lattice/lattice-swarm)
Your own site
<a href="https://agentmods.dev/skills/sectersion/lattice/lattice-swarm"><img src="https://agentmods.dev/badge/skills/sectersion/lattice/lattice-swarm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lattice-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/sectersion/lattice/lattice-swarm"><img src="https://agentmods.dev/badge/skills/sectersion/lattice/lattice-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,703 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.02703
Opus 5 $0.00055 $0.01352
Sonnet 5 $0.00022 $0.00541
Haiku 4.5 $0.00011 $0.00270

Measured 8d ago against content hash ad117e8284b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

lattice-swarm scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s -X POST $BASE/register -d '{"name":"seeder"}' # {id:1,...}

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:<port>/health # {"status":"ok","threads":0,...}
skills/lattice-swarm/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lattice swarm orchestration

The lattice skill documents the participant side of the API (register, reply, claim, subscribe, ack). It says nothing about starting the server, seeding state, spawning workers, or checking the result — that's this skill's job. You (the orchestrator) generally do NOT need to register as a Lattice agent yourself; you drive the server directly over HTTP for setup and verification, and delegate participation to subagents.

1. Start the server

Run the published Docker image (ghcr.io/sectersion/lattice), not npm run build — the swarm is meant to coordinate agents working in any codebase, not just this repo, so don't assume a local checkout of Lattice exists:

docker run -d --name lattice-swarm -p <port>:3000 \
  -v <scratch-dir>:/data \
  ghcr.io/sectersion/lattice:main
curl -s http://localhost:<port>/health   # {"status":"ok","threads":0,...}

Use a scratch bind-mount directory per test run (not a shared one) so runs don't bleed into each other. There is no delete endpoint — to reset between runs, stop the container and remove the scratch dir's DB file, then restart:

docker rm -f lattice-swarm

2. Seed roles and threads

Decide the role pipeline first — a fixed {role: count} map (e.g. {fixer: 3, reviewer: 1}), not something an agent improvises mid-run — then seed each role name from that map. Register one seeder identity and use it for all setup calls — role catalog entries and thread creation both require an identified agent:

curl -s -X POST $BASE/register -d '{"name":"seeder"}'          # {id:1,...}
curl -s -X POST $BASE/roles -d '{"name":"seeder","id":1,"role":"fixer"}'
curl -s -X POST $BASE/roles -d '{"name":"seeder","id":1,"role":"reviewer"}'
curl -s -X POST $BASE/threads -d '{"name":"seeder","id":1,"title":"status","body":"..."}'
curl -s -X POST $BASE/threads -d '{"name":"seeder","id":1,"title":"bug-1","body":"...","wants_role":"fixer"}'

Create any shared coordination threads (a "status" thread, a "plans" thread for review handoffs) before spawning workers — a worker that posts to a thread that doesn't exist yet just gets "unknown thread, check thread id".

Read the full file on GitHub · 225 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 225 lines · 110 tokens per session scan B ad117e8284b1

Subscribe to this mod's changes

lattice-swarm is a skill published in the GitHub repository sectersion/lattice (2 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 2,703 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

gemini

Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…

nowork-studio/notfair-plugin · 184 tokens

content-planner

GSC-driven content calendar. Pulls real Search Console data, finds the highest click-potential opportunities (striking-distance queries at positions 5-20, unanswered query intent, related-keyword expansions), and produces a dated, prioritized content calendar — ready to hand to /content-writer. Use when the user asks…

nowork-studio/notfair-plugin · 123 tokens

meta-tags-optimizer

Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…

nowork-studio/notfair-plugin · 91 tokens

setup-cms

Connect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross- references CMS content against Google Search Console data. Use whenever the user says "connect my…

nowork-studio/notfair-plugin · 111 tokens

broken-link-checker

Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".

nowork-studio/notfair-plugin · 72 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens