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/cosmix/loom/loom-data-validationnpx skills add cosmix/loom --skill loom-data-validationgit 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-data-validation)<a href="https://agentmods.dev/skills/cosmix/loom/loom-data-validation"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-data-validation.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 | $0.00023 | $0.03954 |
| Opus 5 | $0.00012 | $0.01977 |
| Sonnet 5 | $0.00005 | $0.00791 |
| Haiku 4.5 | $0.00002 | $0.00395 |
Grade A, and why
loom-data-validation 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 today.
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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Validation
Overview
Validate untrusted data at trust boundaries before it flows into your system. This skill covers schema libraries (Zod/Pydantic/Joi/JSON Schema), coercion pitfalls, context-dependent output encoding, injection/XSS/DoS defenses, and pipeline/ML feature validation.
Core principles (read first)
- Parse, don't validate. A validator that returns
boolthrows away work — the caller re-parses or trusts blindly. Return a typed value (Result<User>,User | errors) so downstream code cannot receive unvalidated data. Schema libraries (Zod.parse, Pydantic.model_validate) do this by construction. - Validate at the boundary, once, then trust the typed value inward. Boundaries: HTTP handlers, queue consumers, file/CLI parsers, pipeline ingestion, cross-service calls.
- Server-side is authoritative; client-side validation is UX only. Never rely on it for security — attackers bypass the client entirely.
- Allowlist > denylist. Enumerate what's permitted (
enum, char classes, known hosts). Denylists (blocking<script>,../,') are always incomplete — encodings, Unicode, and case defeat them. - Canonicalize before validating. Normalize Unicode (NFC), lowercase host, resolve
./..in paths, decode percent-encoding — then check. Validating raw input lets%2e%2e%2for.(fullwidth) slip past. - Encoding ≠ validation. Validation decides accept/reject; encoding makes a value safe for a specific sink (HTML vs attribute vs JS vs URL vs shell vs SQL). A value can be valid and still need encoding at every sink.
- Limits are validation. Cap length, array size, object depth, and total payload bytes to stop DoS (JSON bombs, deeply nested payloads, ReDoS amplification).
Zod (TypeScript)
safeParse returns a discriminated result (no throw); parse throws ZodError. Prefer safeParse at boundaries.
import { z } from "zod";
const CreateUser = z
.object({
email: z.string().trim().toLowerCase().email().max(255),
password: z.string().min(12).max(128)
.regex(/[a-z]/).regex(/[A-Z]/).regex(/\d/).regex(/[^A-Za-z0-9]/),
role: z.enum(["user", "admin", "moderator"]).default("user"),
tags: z.array(z.string().max(50)).max(10).default([]),
age: z.number().int().min(13).max(150).optional(),
})
.strict(); // reject unknown keys → blocks mass-assignment/overposting
type CreateUserIn = z.input<typeof CreateUser>; // pre-transform
type CreateUserOut = z.output<typeof CreateUser>; // post-transform (use this downstream)
const parsed = CreateUser.safeParse(req.body);
if (!parsed.success) {
const errors = parsed.error.issues.map((e) => ({ field: e.path.join("."), message: e.message }));
return res.status(422).json({ errors });
}
const user = parsed.data; // fully typed + validated
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.
- today Changed · -33 tokens per session 69bca7efcd3c
- 3d ago First seen · 268 lines · 56 tokens per session scan A be250cdc2e3e
loom-data-validation is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 3,954 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
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
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
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.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
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.