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 agentmods add skills/rekabytes/opencode-skills/securitynpx skills add rekabytes/opencode-skills --skill securitygit clone --depth 1 https://github.com/rekabytes/opencode-skillsWhat 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 | $0.00017 | $0.03088 |
| Opus 5 | $0.00009 | $0.01544 |
| Sonnet 5 | $0.00003 | $0.00618 |
| Haiku 4.5 | $0.00002 | $0.00309 |
Grade A, and why
security 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 yesterday.
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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Patterns
1. Authentication
Current State
- Frontend: Logto (OAuth/OIDC) handles user sessions
- Backend:
protectedProcedureexists but NEVER used - All 15 routers use
publicProcedure(INSECURE for user data)
Code: protectedProcedure vs publicProcedure
// CURRENT (INSECURE) - used everywhere in this codebase
export const userRouter = router({
getProfile: publicProcedure
.input(z.object({ userId: z.string() }))
.query(({ input }) => {
// ❌ Anyone can access any user's profile!
return prisma.user.findUnique({ where: { id: input.userId } });
}),
});
// SHOULD BE - using protectedProcedure
export const userRouter = router({
getMyProfile: protectedProcedure
.query(({ ctx }) => {
// ✅ Only authenticated users can access
// ctx.user is guaranteed to be populated
return prisma.user.findUnique({ where: { id: ctx.user.id } });
}),
});
Auth Context (trpc.ts)
// Current state - ctx.user is ALWAYS null!
export const createContext = async ({ req, res }) => {
return {
req,
res,
prisma,
user: null, // Will be populated when token verification is implemented
};
};
// Protected procedure always throws UNAUTHORIZED
export const protectedProcedure = t.procedure.use(async function isAuthed(opts) {
const { ctx } = opts;
if (!ctx.user) {
throw new TRPCError({ code: 'UNAUTHORIZED' });
}
return opts.next({ ctx: { user: ctx.user } });
});
Rules
- ✅ Use
protectedProcedurefor any user-specific data - ✅ Use
publicProcedureonly for truly public data (game info, item catalogs) - ❌ NEVER use
publicProcedurefor: user profiles, settings, private data, mutations
2. Input Validation
Current Approach
- Zod on ALL inputs (this is good)
- Example patterns from codebase:
// String with length limits
z.string().min(3).max(80)
z.string().email()
z.string().uuid()
z.string().optional()
// Numbers with bounds
z.number().min(1).max(100)
z.number().min(1).max(50).default(20)
// Booleans with defaults
z.boolean().default(false)
// Enums for fixed values
z.enum(['OPEN', 'CLOSED', 'IN_PROGRESS'])
z.enum(['RANKED', 'CASUAL', 'CUSTOM', 'TOURNAMENT'])
// Arrays
z.array(z.string())
z.array(z.string()).min(1)
// Objects with nested validation
z.object({
user: z.object({
id: z.string(),
username: z.string().optional(),
avatarUrl: z.string().optional(),
avatarConfig: z.record(z.string(), z.any()).optional(),
isGuest: z.boolean().default(false),
})
})
// Nullable and optional
z.string().nullable()
z.string().optional()
z.string().optional().nullable()
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.
- yesterday First seen · 458 lines · 17 tokens per session scan A 374cb41df90d
security is a skill published in the GitHub repository rekabytes/opencode-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 3,088 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…