Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kangig94/coral --skill equipgit clone --depth 1 https://github.com/kangig94/coralWrote 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/kangig94/coral/equip)<a href="https://agentmods.dev/skills/kangig94/coral/equip"><img src="https://agentmods.dev/badge/skills/kangig94/coral/equip.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.03350 |
| Opus 5 | $0.00006 | $0.01675 |
| Sonnet 5 | $0.00002 | $0.00670 |
| Haiku 4.5 | $0.00001 | $0.00335 |
Grade A, and why
equip 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Equip
Install and configure Coral companion tooling for Claude Code.
Verb Mapping
/equip <pkg>->coral-cli expansion equip <pkg>/equip --list->coral-cli expansion list/equip --update <pkg>->coral-cli expansion update <pkg>/equip uninstall <pkg>->coral-cli expansion unequip <pkg>/equip info <pkg>->coral-cli expansion info <pkg>/equipretired-residue cleanup diagnostics map to the publiccoral-cli expansion remove-catalog <pkg>command.
Runtime Model
coral-cli expansion manages engines through the Expansion lifecycle. Engine identity is package-local; commands should route by declared metadata (id, tier, fills, status) instead of hard-coding package semantics.
fillsdeclares the runtime binding(s) an engine can provide, such askb.fts,kb.vector, orkb.embedding.- If an engine fills
kb.vector, vector search can use it for vector queries. If no vector engine is equipped, vector queries fail withbinding_emptyuntil a vector engine is equipped. - If an engine fills
kb.embedding, engines that require embeddings can use that binding after the embedder is equipped. - If an engine fills
kb.fts, text search can use it for full-text queries.
Tier Semantics
coral-cli expansion list and coral-cli expansion info <pkg> expose tier on engine entries.
| tier | Status source | User verbs |
|---|---|---|
bundled |
Coordinator bundled fallback pass; list/info show tier: 'bundled', status: 'equipped' |
equip and unequip return expansion_bundled_immutable |
installed |
Installed-tier state row; list/info show tier: 'installed' plus state-row-derived status |
equip, unequip, and update manage install and activation |
Bundled engines auto-equip at coordinator boot via the bundled fallback pass. They do not appear in expansion_state (that table tracks installed-tier engines only). See coral-cli expansion list for status.
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 · 160 lines · 12 tokens per session scan A c792fc58b6e2
equip is a skill published in the GitHub repository kangig94/coral (11 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 3,350 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 2026-08-30.
Other skills, from other repositories
deployment
This skill should be used when shipping an app to production — setting up CI/CD, deploys, preview environments, error monitoring, environment separation, or rollback. Trigger phrases include "deploy this", "set up CI/CD", "GitHub Actions", "add error tracking", "set up Sentry", "monitor production", "staging…
api-design
This skill should be used when designing or building an API — endpoints, routes, request/response shapes, error formats, pagination, versioning, or deciding REST vs GraphQL. Trigger phrases include "design the API", "build an endpoint", "REST or GraphQL", "how should I structure my routes", "API error format"…
architecture-primer
This skill should be used when the user wants to design, plan, or decide the architecture of a system, app, or platform from scratch. Trigger phrases include "how do I structure this", "what architecture should I use", "how does this scale", "monolith or microservices", "what database", "what stack", "design the…
saas-router
This skill should be used FIRST whenever the user wants to create, build, design, ship, or prototype any digital product — a SaaS, web app, platform, MVP, landing page, sales page, dashboard, admin panel, backoffice, internal tool, API, database, auth, payments, or any user interface. Trigger phrases (English) include…
data-modeling
This skill should be used when designing a database schema, modeling data, choosing a database, planning migrations, or setting up multi-tenancy for a SaaS. Trigger phrases include "design the database", "model this data", "what database should I use", "schema for", "multi-tenant", "tenant isolation", "add an index"…
payments
This skill should be used when adding payments, subscriptions, billing, or pricing to a SaaS — Stripe integration, checkout, plans, the customer portal, webhooks, or deciding a pricing model. Trigger phrases include "add Stripe", "accept payments", "add a subscription", "charge users", "pricing tiers", "checkout"…