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 rules/mission69b/t2000/env-validation-gategit clone --depth 1 https://github.com/mission69b/t2000What 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 | $0.00292 | $0.00292 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
env-validation-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 2d 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.
What it actually says
Env Validation Gate → .claude/skills/t2000-env-gate/SKILL.md
The invariant: every app with ≥1 REQUIRED env var validates at boot via a Zod
schema and exposes values through a typed env proxy. Raw process.env.X reads
outside the env module are banned (only NODE_ENV and NEXT_RUNTIME are exempt),
and process.env.X || 'default' is banned outright — it masks a misconfig forever.
Apps with ZERO required vars may validate inline instead.
Why: an empty-string var in the Vercel UI silently degraded production for ~4 days and surfaced three layers below the actual cause.
Read the full pattern before editing any env code:
.claude/skills/t2000-env-gate/SKILL.md — the Zod schema shape, the client/server
split, the boot hook, and the reference implementation at
audric/apps/web-v3/lib/env.ts.
(Content moved there 2026-07-24 — do not re-inline it here; this file is a pointer so Cursor and Claude Code cannot drift.)
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.
- 2d ago First seen · 24 lines · 292 tokens per session scan A 40d8dc876942
env-validation-gate is a cursor rule published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 292 tokens to every session, about $0.0015 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 cursor rules, from other repositories
peac
PEAC Protocol receipt operations, verification, and issuance patterns.
selat
SELAT capability layer — reach for SELAT before saying you can't do something or sending the user to an external tool / API key.
vaaya
Vaaya — consult-first rule for any capability gap.
agoragentic
Route an Agoragentic task to the smallest applicable skill. Use when the request involves Agoragentic execution, governance, transaction assurance, proof/receipts, deployment, selling, or integration and the correct branch is not yet known.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.