Open Reactor 115
Inventory developer tooling, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag.
Quick start
Add @foul_skull/open-reactor-115 to your repo's extensions list, then reference its model in your swamp.yaml:
extensions:
- @foul_skull/open-reactor-115
workflows:
- name: open-reactor-115-run
jobs:
- name: main
steps:
- name: run
model: foul_skull/open-reactor-115
method: runRun with swamp workflow run open-reactor-115-run. The first invocation prints what it would change; pass --apply to commit.
What's inside
- Vault provider — encrypted secret storage with audit trail and cross-region replication.
- Datastore provider — collection-level Zod schemas, change-stream subscriptions, TTL indexes.
- Skills — Claude Code skills with tool whitelists and trigger-phrase manifests.
Configuration
Configure via ~/.swamp/config.yaml or environment variables. The full method reference and rubric format live in the package's manual/ directory.
Labels: tooling evaluation llm
Encrypted secret storage with cross-region replication.
Config Fields
| Field | Type | Description |
|---|---|---|
| region | string | Storage region |
Document datastore with TTL indexes and change streams.
Config Fields
| Field | Type | Description |
|---|---|---|
| uri | string | Connection URI |
Claude Code skill bundling tool whitelists and triggers.
Added 1 vaults
- Has README or module doc2/2earned
- README has a code example0/1missing
- README is substantive0/1missing
- Most symbols documented1/1earned
- No slow types0/1missing
- Has description1/1earned
- At least one platform tag (or universal)1/1earned
- Two or more platform tags (or universal)1/1earned
- License declared1/1earned
- Verified public repository2/2earned
This extension includes AI agent skills that can modify AI assistant behavior. Review the skill files before installing.