Core Vault 99
Pull developer tooling, normalize the shape, and stream into your downstream pipeline. Pagination is automatic.
Quick start
Add @marsh_beast/core-vault-99 to your repo's extensions list, then reference its model in your swamp.yaml:
extensions:
- @marsh_beast/core-vault-99
workflows:
- name: core-vault-99-run
jobs:
- name: main
steps:
- name: get
model: marsh_beast/core-vault-99
method: getRun with swamp workflow run core-vault-99-run. The first invocation prints what it would change; pass --apply to commit.
What's inside
- Typed models — Zod-validated arguments, structured outputs, and a manifest the agent can reason about.
- Composable workflows — wire methods into multi-step DAGs with retry, idempotency, and per-step logs.
- 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 llm claude-code
| Argument | Type | Description |
|---|---|---|
| limit | number | Maximum results to return |
| Argument | Type | Description |
|---|---|---|
| limit | number | Maximum results to return |
| force? | boolean | Skip confirmation and apply immediately |
| Argument | Type | Description |
|---|---|---|
| force | boolean | Skip confirmation and apply immediately |
| dryRun | boolean | Compute changes without applying them |
| Argument | Type | Description |
|---|---|---|
| limit | number | Maximum results to return |
| force? | boolean | Skip confirmation and apply immediately |
Composed workflow with retry and idempotency.
Composed workflow with retry and idempotency.
Claude Code skill bundling tool whitelists and triggers.
- 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 repository0/2missing
This extension includes AI agent skills that can modify AI assistant behavior. Review the skill files before installing.