Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add eunji-jessi-jung/reef/plugin install reefWrote 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/eunji-jessi-jung/reef/source)<a href="https://agentmods.dev/skills/eunji-jessi-jung/reef/source"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/source/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/eunji-jessi-jung/reef/source"><img src="https://agentmods.dev/badge/skills/eunji-jessi-jung/reef/source.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 | $0.00015 | $0.05280 |
| Opus 5 | $0.00008 | $0.02640 |
| Sonnet 5 | $0.00003 | $0.01056 |
| Haiku 4.5 | $0.00002 | $0.00528 |
Grade A, and why
source 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 8d 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 — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reef:source
Extract complete API specifications and entity-relationship diagrams from source codebases. Uses a tiered protocol — try the fastest reliable method first, fall back gracefully. Caches successful recipes for repeat runs.
This skill runs in parallel with snorkel after init:
┌→ snorkel (structural artifacts)
init → ──┤ → scuba → deep
└→ source (API specs + ERDs)
Snorkel writes to artifacts/. Source writes to sources/apis/ and sources/schemas/. No file conflicts. Scuba uses both.
Output Structure
Source extraction writes to a service-grouped directory structure, using the service mappings from .reef/project.json:
sources/
apis/
{service}/
{sub}/ # sub-application (if applicable)
openapi.json # always OpenAPI 3.x JSON, regardless of extraction tier
openapi.meta.json # extraction metadata (tier, method, source path, timestamp)
schemas/
{service}/
{sub}/
schema.md # Mermaid ERD + field tables
infra/
{service}/
storage.md # cloud storage path patterns and bucket layout (if detected)
runtime.md # Docker/K8s topology and env vars (if detected)
queues.md # message queue topics and task definitions (if detected)
Examples with service groupings:
sources/
apis/
payments/
gateway/openapi.json # tier 2: runtime extracted
ledger/openapi.json # tier 2: runtime extracted
admin/openapi.json # tier 2: runtime extracted
orders/
openapi.json # tier 2: runtime extracted (single-app repo)
platform/
auth/openapi.json # tier 2: runtime extracted (swag)
analytics/openapi.json # tier 2: runtime extracted
pipeline/
gateway/openapi.json # tier 2: runtime extracted
schemas/
payments/
gateway/schema.md
ledger/schema.md
orders/
schema.md
platform/
auth/schema.md
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.
- 8d ago First seen · 515 lines · 15 tokens per session scan A 2ddbcd94b334
source is a skill published in the GitHub repository eunji-jessi-jung/reef (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 5,280 once invoked, about $0.0001 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
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…