Clean scanStatic scanned
Scaffolds OpenUI agent apps, mints Cloud API keys and turns component libraries into model prompts.
45.8k installs/moMIT
Agentopology
nadavnaveh · Template
Lets you define multi-agent systems as code. You write a topology file that says which agents work, when they work and what they know, then validate it, view it as a graph and scaffold platform-native configuration from it. Alternatively, a plan command skips file generation and gives the coding agent already in your session a brief to run the team with its own sub-agents, though hooks, MCP servers, triggers, schedules and per-agent tool limits are only set up by scaffolding. A Claude Code skill drafts the topology from a plain-English description.
Written by ooruby from the README of agentopology 0.5.2.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
The team definition lives in one file, so you stop hand-maintaining separate agent configuration for each platform.
What you could do with it
- Ask the Claude Code skill for a code review team with an analyser, a security scanner and a reviewer.
- Run a team on a task such as adding rate limiting to an API, using your coding agent's own sub-agents and no generated files.
- Scaffold one topology for several platforms, or open it as an interactive graph to see how the agents connect.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (skill/scripts/visualize.ts:13)
- synchronous shell execution (skill/scripts/visualize.ts:86)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
- Row-level security
- nothing to read
- No Supabase migrations in the 40 files of the published package read on 2026-10-11, short of every file it ships: the nightly reading stops at 40 files or 4 MB, so there was nothing for this check to read.
- Not covered: A reading of files cannot prove a policy is enforced at run time: whether these migrations were applied, whether row-level security was switched on another way (the dashboard, SQL run by hand), or what a table holds. A database only the app's own server can reach (SQLite, or Postgres behind a server that holds the only connection) needs no row-level security for this reason, and its migrations are not read.
- Object-level authorisation
- nothing to read
- No Supabase migrations in the 40 files of the published package read on 2026-10-11, short of every file it ships: the nightly reading stops at 40 files or 4 MB, so there was nothing for this check to read.
- Not covered: Whether the app means every account to edit everything (an admin tool whose only account is its owner's), whether sign-up is open (a dashboard setting), and anything about a policy whose expression looks at the row. Whether the migrations were applied is not known. Policies that let anyone read every row are not counted here.
- CORS configuration
- no match, 39 code files read
- App check set 1.0 matched nothing across 39 code files, 40 files of the published package read on 2026-10-11, short of every file it ships: the nightly reading stops at 40 files or 4 MB.
- Not covered: Whether it matters. A server that checks a token sent in a header gives a foreign page nothing it could not do without the browser, and a server bound to the loopback address is reachable only from pages open on the same machine (which is still every page that machine opens). A value chosen at run time, such as a variable that falls back to *, is not read: the hand count found one such server, and it is not in the figure.
- Not covered: Whether the server reads cookies at all, whether the echo is guarded by a check this reading does not follow, and anything decided at run time.
- No shipped credentials
- no match, 40 files read
- App check set 1.0 matched no credential in a format it recognises, bundles included, across the 40 files of the published package read on 2026-10-11, short of every file it ships: the nightly reading stops at 40 files or 4 MB.
- Not covered: Whether a key still works (none is ever tried, because trying one would be using it), credentials in formats the check does not name, anything in a repository's history, and files the nightly reading does not reach when a package is over its caps.
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
App checks are read with app check set v1.0, published with every rule, what it does not cover and how often it has been wrong.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
The declarative language for multi-agent systems. Write once, scaffold for any platform.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.5.2, the file with digest sha512-KO2VZuzBqiCWQO80TXSqeO0INCvZ98UU0l2ZPYAyWs/JgU9A+DrUmyikFKt6dPqi8DgvNFb45zYrMH+bI0XumA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y agentopology@0.5.2Pinned to 0.5.2, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
881 installs last month · no published advisories · version current · checked 2026-10-11
Where this came from
- Registry
- npm
- Package
- agentopology
- Version read
- 0.5.2
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/agentopology)About this listing
- Kind
- Template
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-07
Similar templates
All templatesVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.