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-authnpx skills add cosmix/loom --skill loom-authgit 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-auth)<a href="https://agentmods.dev/skills/cosmix/loom/loom-auth"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-auth.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 | $0.00031 | $0.03612 |
| Opus 5 | $0.00015 | $0.01806 |
| Sonnet 5 | $0.00006 | $0.00722 |
| Haiku 4.5 | $0.00003 | $0.00361 |
Grade A, and why
loom-auth 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication & Authorization
Authentication proves who you are; authorization decides what you may touch. Authorization is where real bugs cluster — broken object-level authorization (IDOR/BOLA) is the #1 API risk (OWASP API Security Top 10). Get object-ownership checks right before polishing token plumbing.
When to Use
Auth is security-critical. Subject designs, token/session lifecycle changes, access-control model changes, and any code handling production credentials to adversarial review against the checklist below. Treat a framework's defaults as untrusted until its documented behavior and configured version are verified.
Scope boundary: this skill is mechanisms. For vuln scanning use loom-security-scan; deep audit loom-security-audit; architecture threats loom-threat-model.
Authorization: IDOR / BOLA (read this first)
Every request that names an object (/orders/123, ?user_id=…, a foreign key in a body) must verify the caller owns or is granted that specific object — authentication ("is logged in") is not authorization. The bug is invisible in tests that only use one account.
// ❌ BOLA: any authenticated user reads any order by guessing the id
app.get("/orders/:id", requireAuth, async (req, res) => {
const order = await db.orders.findUnique({ where: { id: req.params.id } });
res.json(order);
});
// ✅ Scope the query by the authenticated principal (and tenant)
app.get("/orders/:id", requireAuth, async (req, res) => {
const order = await db.orders.findFirst({
where: { id: req.params.id, userId: req.user.id }, // ownership in the WHERE
});
if (!order) return res.status(404).end(); // 404 not 403: don't confirm existence
res.json(order);
});
Rules: enforce ownership/tenant in the query filter, not a post-fetch if; check on writes and nested/batch operations too; never trust an id/role/tenant from the client body (mass-assignment → privilege escalation); default-deny. In multi-tenant systems scope every query by tenant_id — a missing tenant filter is cross-tenant data leakage.
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 Changed · -48 tokens per session 486ae57ea08a
- 5d ago First seen · 302 lines · 79 tokens per session scan A 392fbb1acc91
loom-auth is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 3,612 once invoked, about $0.0002 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
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.
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.
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.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…