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 mission69b/t2000 --skill t2000-env-gategit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/t2000-env-gate)<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-env-gate"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-env-gate.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.01125 |
| Opus 5 | $0.00060 | $0.00562 |
| Sonnet 5 | $0.00024 | $0.00225 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
t2000-env-gate 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Env Validation Gate (cross-app standard)
CLAUDE.md rule 7 states the invariant and the zero-required-vars carve-out.
This is the pattern behind it.
Why this rule exists
April 2026: an audric production deploy ran ~4 days with BLOCKVISION_API_KEY=""
(empty string in the Vercel UI), silently degrading every BlockVision-backed
feature. It surfaced as "the LLM thinks the user has no DeFi positions" — three
layers below the actual misconfig. An empty string is truthy-adjacent enough to
pass every if (!key) guard and every || fallback, so nothing failed loudly.
The contract
- Define a
lib/env.ts(Next apps) orsrc/env.ts(servers) Zod schema. - Required vars use
z.string().trim().min(1, …)— empty string is invalid. - Optional vars normalize empty/whitespace →
undefined. - Schema runs at first import; trigger that import from a boot-time hook:
- Next.js →
instrumentation.tsregister() - Node server → top of
server.ts/index.ts
- Next.js →
- Export a typed
envproxy that throws on server-only access from the client. - Enforce: ESLint
no-restricted-syntaxon rawprocess.env.Xoutside the env module (gateway), or Biome + code review (audric web-v3).
Canonical reference implementation
audric/apps/web-v3/lib/env.ts + audric/apps/web-v3/instrumentation.ts.
import { z } from 'zod';
const requiredString = z.string().trim().min(1, 'must be a non-empty string');
const optionalString = z.string().optional().transform((v) =>
v === undefined ? undefined : v.trim().length > 0 ? v.trim() : undefined,
);
const serverSchema = z.object({
ANTHROPIC_API_KEY: requiredString,
// …
});
const clientSchema = z.object({
NEXT_PUBLIC_GOOGLE_CLIENT_ID: requiredString,
// …
});
// Literal references — Next.js static replacement requires this shape:
const runtimeEnv = {
ANTHROPIC_API_KEY: process.env.ANTHROPIC_API_KEY,
NEXT_PUBLIC_GOOGLE_CLIENT_ID: process.env.NEXT_PUBLIC_GOOGLE_CLIENT_ID,
// …
};
const isServer =
typeof process !== 'undefined' &&
(typeof process.versions?.node === 'string' ||
process.env?.NEXT_RUNTIME === 'edge');
const fullSchema = z.object({ ...serverSchema.shape, ...clientSchema.shape });
const parsed = (isServer ? fullSchema : clientSchema).safeParse(runtimeEnv);
if (!parsed.success) {
// Format ALL issues + the settings URL — operators fix in one click.
throw new Error(/* formatted block */);
}
export const env = new Proxy(parsed.data, {
get(target, prop) {
if (!isServer && SERVER_ONLY_KEYS.has(prop as string)) {
throw new Error(`[env] Cannot access server-only var '${String(prop)}' from the client`);
}
return target[prop as keyof typeof target];
},
});
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.
- 8d ago First seen · 121 lines · 120 tokens per session scan A 01499c3cb141
t2000-env-gate is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 1,125 once invoked, about $0.0006 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-payment-stats
Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…
app
Use when the user asks about interacting with the app's API — querying data, creating resources, checking status. This skill covers all MCP tools and REST endpoints exposed by the server.
swarmwage-hire
Discover, inspect, dry-run, hire, and pay AI capabilities through Swarmwage. Start with wallet-free capability search and x402 reliability checks; use a dedicated USDC wallet only for real hires or paid external x402 calls.
swarmwage-publish
Publish your agent's capabilities to the Swarmwage registry and earn USDC for each call. Lets your agent advertise services (image generation, audio transcription, charting, custom domain workflows…) on the open agent hire protocol — other AI agents discover you, hire you with one function call, and pay you in USDC on…
phone
Use when the user wants phone-number intelligence (lookup, carrier, line type, SIM-swap / call-forwarding fraud signals), US/CA number provisioning (rent a phone number), or outbound AI voice calls (Bland.ai under the hood — schedule, confirm, follow-up). Pay per call in USDC.
data-engineering
Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…