EXTENSIONS
Gateway Api
The Kubernetes Gateway API, read as swamp data: Gateways, HTTPRoutes and GatewayClasses with their conditions, through kubectl. Read-only.
Http
One HTTP or HTTPS endpoint, asked whether it answers, as swamp data.
Zernio
Vault-backed Zernio account verification plus approval-bound, schedule-only Facebook and Instagram publishing.
Read Only Investigation
Creates deterministic, bounded authorization plans for read-only investigations without executing queries, invoking providers, or mutating production systems.
Observability Workflows
Generic read, normalization, digest, and transition-only alert workflows for Swamp observability adapters.
Mysql Client
Read-only client for MySQL and Aurora MySQL. Checks connectivity, runs
Platform Health
One workflow, `@dataverket/platform-health`, that checks the forges, S3 gateways and HTTP endpoints a repository names and fails when one of them is down.
Uptime Kuma
Read-only Uptime Kuma monitor history for triage: the last N heartbeats of one monitor -- status, time, message, ping -- plus a summary of the current status, since when, and how many times it changed in the window. Kuma has no REST endpoint for heartbeat history, and its socket.io API needs the instance's only kind of login, an administrator, so any credential that can read history can also delete monitors and read notifier secrets. This model instead reads kuma.db over SSH with the host's python3, opening the database mode=ro with PRAGMA query_only=ON so SQLite itself refuses any write, and selects named columns from the monitor and heartbeat tables only: never notifier settings, credentials, monitor URLs or hostnames, or heartbeat response bodies. Monitors are found by id or by name (exact, else a unique case-insensitive substring; ambiguity is an error listing the candidates). It needs no Kuma login, never enters the container, never copies the database off the host, and has no write method.
Docker Ps
A read-only container listing of a Docker host over SSH, narrow enough to hand to an unattended triage agent. It answers the first question an alert usually raises -- what is running on that host, and which container holds that port -- with name, image, state, status, published ports and creation time per container. It runs `docker ps` with an explicit, per-field `--format` template and rebuilds each row from those fields alone, so no environment variable and no label value ever leaves the host: `docker inspect` returns every container's environment, which is where compose files keep database passwords and API tokens, and `docker ps --format '{{json .}}'` includes the Labels field. The type has exactly one method and no free-form command or format argument, so a model instance exposes no write verb at all. Host key checking stays on by default.
Log Tail
Read the last lines of a log chosen by NAME from an allowlist fixed in the model definition, with secret values redacted. Built for an alert-triage agent that has no shell: an alert names a log, the cause is usually one line near its end, and the alternatives are a human tailing it for the agent or a general file-read tool that can read anything. The caller passes a name, never a path; the name-to-path map lives in the definition, where only its owner can change it. A name is matched with Object.hasOwn and a name that is not name-shaped is never echoed, because `--input name=@file` would otherwise turn a refusal into a read. The configured path must be absolute, normalised, a regular file, not a symlink and equal to its own realpath, and the opened file's device and inode must match the lstat taken before the open, so a symlink swapped in between is refused rather than followed. Output is capped at 200 lines. Redaction drops values and keeps names (`password=[REDACTED]`) across key=value, JSON, YAML, CLI flags, URL userinfo, Authorization headers and bare token shapes, and fails closed: a line mentioning a password manager CLI or a private key is withheld whole, a line still credential-shaped after redaction is withheld whole, and an error in redaction fails the method. Both methods are read-only.
Sleeper
Read fantasy league state from the Sleeper platform's public read-only API — no key, no OAuth, no write surface. Resolve a username to a user ID, list leagues and drafts, and read a league in depth: settings and scoring, rosters with owners joined and standings derived, weekly matchups paired head to head, the transaction log, traded picks (league-wide and per draft), playoff brackets, the draft board, and league-wide add/drop trends. Player IDs are resolved to names from a locally cached catalogue, and a missing record (which Sleeper reports as HTTP 200 with a null body) fails loudly instead of reading as empty.
Architecture Development
Read-only ArchiMate architecture review through complete revision-coherent model evidence, selectable specialist and domain lenses, deterministic synthesis, and durable user-directed dialogue.
Active Directory
Read-only inventory of an on-premises Active Directory domain over LDAP. Collects users, groups, and computers straight from a domain controller — no Windows host, no WinRM, no PowerShell — and decodes what AD returns raw: FILETIME timestamps, binary SIDs and GUIDs, userAccountControl and groupType bitmasks. Handles paged searches and member range retrieval, so domains over 1000 objects and groups over 1500 members are not silently truncated. Methods: inventory, list_users, list_groups, list_computers.
Mailgun Readonly
Read-only Mailgun models — GET requests only, no write capability
Doc Fact Checker
Fact-check one Markdown document through a provider-neutral, read-only adapter. Kiro CLI is the default provider; Claude CLI is supported when explicitly selected. Repository and optional web capabilities are recorded separately, with no provider fallback.