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-istiogit 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-istio)<a href="https://agentmods.dev/skills/cosmix/loom/loom-istio"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-istio.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Supply Chain · line 122 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00022 | $0.10705 |
| Opus 5 | $0.00011 | $0.05352 |
| Sonnet 5 | $0.00004 | $0.02141 |
| Haiku 4.5 | $0.00002 | $0.01070 |
Grade B, and why
loom-istio scanned grade B with 2 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 5d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -L https://istio.io/downloadIstio | sh - Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L https://istio.io/downloadIstio | sh - How it starts
The opening of the file, as written. The whole thing — 1,206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Istio Service Mesh
Overview
Istio is a service mesh: Envoy proxies intercept all service traffic to provide traffic management, mTLS, and observability with no app changes. Two data-plane models — pick deliberately:
- Sidecar (classic): one Envoy per pod; full L7 everywhere; higher per-pod CPU/mem and injection restart cost.
- Ambient (GA in 1.24): per-node ztunnel does L4 mTLS + L4 auth/telemetry automatically; waypoint proxies add L7 only where deployed. Lower overhead, no injection restarts, but L7 features silently no-op without a waypoint. See Currency.
Quick Reference: Common Tasks
| Task | Resources | Section |
|---|---|---|
| Enable mTLS between services | PeerAuthentication | mTLS PeerAuthentication |
| Route traffic to new version | VirtualService + DestinationRule | Traffic Splitting for Canary |
| Add circuit breaker | DestinationRule (outlierDetection) | Circuit Breaker and Retry |
| Configure retries/timeouts | VirtualService (retries, timeout) | Circuit Breaker and Retry |
| Expose service to internet | Gateway + VirtualService | Gateway and VirtualService |
| Control egress traffic | Sidecar + ServiceEntry | Sidecar Resource for Egress |
| Add authorization rules | AuthorizationPolicy | AuthorizationPolicy for RBAC |
| Configure load balancing | DestinationRule (loadBalancer) | DestinationRule with Traffic Policies |
| Test resilience | VirtualService (fault injection) | Fault Injection for Testing |
Architecture Components
Control Plane (istiod)
istiod is a single unified binary (since Istio 1.5) that performs:
- Service discovery and configuration distribution (xDS to the Envoy sidecars)
- Certificate authority for mTLS
- Sidecar injection (mutating admission webhook)
- Configuration validation
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.
- 5d ago Changed · -37 tokens per session 2a09455f1c0e
- 8d ago First seen · 1,206 lines · 59 tokens per session scan B 30dbbf67dcba
loom-istio is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 10,705 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, 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
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
Agent Design Principles
A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.