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.
npx skills add ludeo-labs/cosmos-os --skill add-servicegit clone --depth 1 https://github.com/ludeo-labs/cosmos-osWrote 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.
[](https://agentmods.dev/skills/ludeo-labs/cosmos-os/add-service)<a href="https://agentmods.dev/skills/ludeo-labs/cosmos-os/add-service"><img src="https://agentmods.dev/badge/skills/ludeo-labs/cosmos-os/add-service/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.
<a href="https://agentmods.dev/skills/ludeo-labs/cosmos-os/add-service"><img src="https://agentmods.dev/badge/skills/ludeo-labs/cosmos-os/add-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.02269 |
| Opus 5 | $0.00046 | $0.01135 |
| Sonnet 5 | $0.00018 | $0.00454 |
| Haiku 4.5 | $0.00009 | $0.00227 |
Grade A, and why
add-service scanned grade A with 0 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a service (or topic) to the Cosmos
Use this skill when the user says "add X to the cosmos", "wire service X into the map", or "add a topic node for Y". This covers adding a standalone capsule — it does not add scenario steps (use the add-scenario skill for that).
What you'll touch
| File | Why |
|---|---|
src/scenarios/services.ts |
Add entries to SERVICES |
src/scenarios/topics.ts |
Add entries to TOPICS (only for topics used in scenario steps) |
src/scenarios/owners.ts |
Team ownership mapping |
src/scenarios/types.ts |
Only if you need a new Tech variant |
src/components/TechIcon.tsx |
Only if you added a new Tech variant |
src/styles/tokens.css |
Only if you need a new --svc-* color hue |
src/map/UICluster.tsx |
Only if the new service is a browser-facing UI surface |
Step 1 — Research the service
Before touching any file, grep and read the service's source code (use an Explore agent for repos not in the workspace). You need:
- What does this service do? (one sentence role)
- What stack does it run on? (framework, language)
- What databases / infra does it use? (Kafka, Redis, Postgres, object storage…)
- What Kafka topics does it produce / consume?
- What HTTP endpoints does it expose or call?
- What other services call it? What does it call?
- What WebSocket connections does it open or accept?
- What is its repository name in your GitHub org?
Only proceed once you can answer all of these from source — never guess.
Step 2 — Map all connections
Before writing any entry, build a connection table. This is the most important step — it determines what goes into desc, what Kafka topics to add, which existing service descriptions to update, and what to flag as missing.
For every connection the new service has, fill in this table:
| Direction | Protocol | Counterpart | Counterpart in cosmos? | Topic in cosmos? |
|---|---|---|---|---|
| → outbound | HTTP | payments |
✅ payments |
n/a |
| ← inbound | Kafka (consume) | orders |
✅ orders |
orders.created ❌ missing |
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.
- 12d ago First seen · 206 lines · 92 tokens per session scan A 9feb0034cf3d
add-service is a skill published in the GitHub repository ludeo-labs/cosmos-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,269 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
architecture-patterns
Software architecture patterns and best practices.
mandu-mcp-create-flow
A specification-first workflow for creating features, resources, routes, or API endpoints. It creates a contract describing the expected structure before generating the code, then verifies the result.
mandu-fs-routes
File-system based routing for Mandu. Use when creating pages, API routes, layouts, or dynamic routes. Triggers on tasks involving app/ folder, page.tsx, route.ts, layout.tsx, [id], [...slug], or URL patterns.
mandu-security
Security best practices for Mandu applications. Use when implementing authentication, authorization, input validation, or protecting against common vulnerabilities. Triggers on guard, auth, CSRF, XSS, or security tasks.