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 shennawardana23/skillme --skill backend-patternsgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/backend-patterns)<a href="https://agentmods.dev/skills/shennawardana23/skillme/backend-patterns"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/backend-patterns/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/shennawardana23/skillme/backend-patterns"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/backend-patterns.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 | $0.00088 | $0.02282 |
| Opus 5 | $0.00044 | $0.01141 |
| Sonnet 5 | $0.00018 | $0.00456 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
backend-patterns 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 9d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Patterns
Structural patterns for server-side code, independent of any one
framework. For the shape of the request/response contract itself, see
api-design; for query- and index-level database patterns, see
postgres-patterns; for structured logs/metrics/traces, see
observability-and-instrumentation.
Layering: handler → service → repository
Keep three concerns separate so each can be tested and changed independently:
// repository: only knows SQL, returns domain types or a wrapped error
type ReservationRepo struct{ db *sql.DB }
func (r *ReservationRepo) ByID(ctx context.Context, hotelID int64, id string) (*Reservation, error) {
const q = `SELECT id, hotel_id, status FROM reservations WHERE hotel_id = $1 AND id = $2`
var res Reservation
if err := r.db.QueryRowContext(ctx, q, hotelID, id).Scan(&res.ID, &res.HotelID, &res.Status); err != nil {
if errors.Is(err, sql.ErrNoRows) {
return nil, fmt.Errorf("reservation %s: %w", id, ErrNotFound)
}
return nil, fmt.Errorf("query reservation %s: %w", id, err)
}
return &res, nil
}
// service: business logic, orchestrates repositories, knows nothing about HTTP
type ReservationService struct{ repo *ReservationRepo }
func (s *ReservationService) Cancel(ctx context.Context, hotelID int64, id string) error {
res, err := s.repo.ByID(ctx, hotelID, id)
if err != nil {
return err
}
if res.Status == StatusCheckedOut {
return fmt.Errorf("cancel reservation %s: %w", id, ErrAlreadyCheckedOut)
}
return s.repo.SetStatus(ctx, hotelID, id, StatusCancelled)
}
// handler: only knows HTTP — decode, call service, map errors to status codes
func (h *Handler) CancelReservation(w http.ResponseWriter, r *http.Request) {
hotelID, id := parseParams(r)
if err := h.svc.Cancel(r.Context(), hotelID, id); err != nil {
writeError(w, err) // maps ErrNotFound -> 404, ErrAlreadyCheckedOut -> 409, else 500
return
}
w.WriteHeader(http.StatusNoContent)
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 229 lines · 88 tokens per session scan A a6b244cd7376
backend-patterns is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,282 once invoked, about $0.0004 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
encore-go-cache
Cache data in Redis from Encore Go using cache.NewCluster and typed keyspaces from encore.dev/storage/cache. Type-safe key/value access with TTLs, atomic increments, and per-keyspace data shapes.
upstash-ratelimit-js
Rate limiting for serverless and edge apps with the @upstash/ratelimit TypeScript/JavaScript SDK backed by Upstash Redis. Use when adding a rate limiter or throttling to an API route, Next.js middleware, Vercel Edge, Cloudflare Workers, or any HTTP endpoint; returning 429 Too Many Requests; choosing between fixed…
laravel-async
Asynchronous and caching rules for Laravel — idempotent queued jobs with retries and backoff, domain events for side effects, queue separation and failure handling, deterministic cache keys with event-driven invalidation, and scheduled tasks that queue rather than block. Use when writing or reviewing jobs, events…
bullmq-docs
Use when users ask how to create, configure, process, schedule, retry, rate-limit, monitor, or troubleshoot BullMQ job queues and workers in Node.js, including queues, workers, jobs, flows, job schedulers, events, telemetry, Redis compatibility, NestJS integration, patterns, or production deployment, especially when…
wp-plugin-performance
Performance guidelines for WordPress plugin development: database optimization, object caching, conditional asset loading, efficient hooks, HTTP requests, WP-Cron, AJAX/REST optimization, and common anti-patterns. Based on official WordPress Developer Resources and WP VIP documentation.
redis-caching
Redis caching, rate limiting, session storage, pub/sub, and production integration patterns for TypeScript, Next.js, NestJS, and Prisma applications. Use when adding cache-aside or write-through caching, rate limiting, session or lock storage, pub/sub fanout, or reviewing Redis key design and TTLs.