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 cosmix/loom --skill loom-golanggit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-golang)<a href="https://agentmods.dev/skills/cosmix/loom/loom-golang"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-golang/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/cosmix/loom/loom-golang"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-golang.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 328 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.06430 |
| Opus 5 | $0.00008 | $0.03215 |
| Sonnet 5 | $0.00003 | $0.01286 |
| Haiku 4.5 | $0.00002 | $0.00643 |
Grade A, and why
loom-golang scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
func fetch(ctx context.Context, url string) ([]byte, error) { How it starts
The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Language Expertise
Overview
Idiomatic, production-grade Go: concurrency, error handling, interfaces, testing, and version-gated behavior. The Foundations below get code working; the Expert Practices section is the higher bar — each item states the mechanism so you can apply it beyond the case shown.
Foundations
Error Handling
// Sentinel errors for identity checks; custom types for structured context.
var ErrNotFound = errors.New("resource not found")
type ValidationError struct{ Field, Message string }
func (e *ValidationError) Error() string {
return fmt.Sprintf("validation on %s: %s", e.Field, e.Message)
}
func fetchUser(id string) (*User, error) {
u, err := db.GetUser(id)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
return nil, fmt.Errorf("user %s: %w", id, ErrNotFound) // wrap w/ %w
}
return nil, fmt.Errorf("fetching user %s: %w", id, err)
}
return u, nil
}
// errors.Is matches by identity down the %w chain; errors.As extracts a type.
var ve *ValidationError
if errors.As(err, &ve) { /* ve.Field, ve.Message */ }
%w vs %v is an API decision — see Expert Practices.
Concurrency
// Worker pool. Go 1.25+: wg.Go does Add(1)+launch+Done atomically (see Expert).
func workerPool(jobs <-chan Job, results chan<- Result, n int) {
var wg sync.WaitGroup
for range n {
wg.Go(func() { // pre-1.25: wg.Add(1); go func(){ defer wg.Done(); ... }()
for job := range jobs {
results <- process(job)
}
})
}
wg.Wait()
close(results) // sender closes, exactly once; never the receiver
}
// Context timeout — always defer cancel() even when the deadline fires.
func fetch(ctx context.Context, url string) ([]byte, error) {
ctx, cancel := context.WithTimeout(ctx, 5*time.Second)
defer cancel()
req, _ := http.NewRequestWithContext(ctx, "GET", url, nil)
resp, err := http.DefaultClient.Do(req)
if err != nil {
return nil, err
}
defer resp.Body.Close()
return io.ReadAll(resp.Body) // drain AND close — see Expert (conn reuse)
}
// select with nil-channel disable: a nil channel blocks forever, so setting a
// drained channel to nil removes it from the select without a sentinel flag.
select {
case v, ok := <-ch:
if !ok { ch = nil; continue }
use(v)
case <-ctx.Done():
return ctx.Err()
}
// RWMutex-guarded state. Pointer receiver is mandatory (copying a Mutex breaks it).
type SafeCounter struct {
mu sync.RWMutex
count map[string]int
}
func (c *SafeCounter) Inc(k string) { c.mu.Lock(); defer c.mu.Unlock(); c.count[k]++ }
func (c *SafeCounter) Get(k string) int { c.mu.RLock(); defer c.mu.RUnlock(); return c.count[k] }
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.
- 6d ago Changed · -26 tokens per session b1ba18076776
- 9d ago First seen · 468 lines · 41 tokens per session scan A 17b3e53a808c
loom-golang is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 6,430 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
authoring-go-sdk-tasks
Writes Airflow task logic in Go using the Airflow Go SDK. Use when the user wants to implement Airflow tasks in Go, asks about BundleProvider/RegisterDags, the bundlev1 Registry/Dag interfaces, registering Go tasks (AddTask/AddTaskWithName), dependency injection by parameter type (context.Context, sdk.TIRunContext…
deploying-go-sdk-bundles
Builds, packs, and deploys compiled Airflow Go SDK bundles so the ExecutableCoordinator can run them. Use when the user wants to compile a Go task bundle, asks about go build, go tool airflow-go-pack, the AFBNDL01 self-contained executable bundle, packing or inspecting a bundle, placing it under executablesroot…
developing-genkit-go
Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming, tool calling, or model providers.
authoring-dags
Workflow and best practices for writing Apache Airflow DAGs. Use when creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a follow-up/downstream task. ANY request shaped like 'add a DAG named X', 'write a pipeline', 'add a task that runs…
jackson-3-migration
Migrer Jackson 2.x til Jackson 3.x (tools.jackson) i Kotlin/Java-prosjekter — automatisert OpenRewrite-pass pluss manuell Kotlin-spesifikk opprydding og verifisering.
wasm
WebAssembly (WASM) integration, WASI, component model, Rust/Go to WASM compilation. Use when implementing WASM modules, browser/edge compute, or polyglot runtime.