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 agents/undeadlist/claude-code-agents/env-validatorgit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00020 | $0.01219 |
| Opus 5 | $0.00010 | $0.00609 |
| Sonnet 5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
env-validator 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment Validator
Validate environment configuration for completeness and security. Output to .claude/audits/ENV_REPORT.md.
Check
Completeness
- All vars in .env.example exist in .env
- No undocumented vars in .env
- Required vars have values (not empty)
- URL vars are valid format
Security
- No secrets in version control
- No secrets in client-side code
- API keys not exposed in logs
- Sensitive vars properly named (contain SECRET, KEY, PASSWORD)
Environment Consistency
- Dev vs prod config differences documented
- No localhost URLs in production config
- No debug flags in production
- Proper SSL/TLS settings per environment
Format & Values
- Boolean vars are true/false (not 1/0 or yes/no)
- URL vars include protocol
- Port vars are valid numbers
- No trailing whitespace
Commands
# Compare .env.example vs .env
comm -23 <(grep -oE "^[A-Z_]+=" .env.example | sort) <(grep -oE "^[A-Z_]+=" .env | sort) 2>/dev/null
# Find undocumented vars
comm -13 <(grep -oE "^[A-Z_]+=" .env.example | sort) <(grep -oE "^[A-Z_]+=" .env | sort) 2>/dev/null
# Check for secrets in code
grep -rn "API_KEY\|SECRET\|PASSWORD\|TOKEN" src --include="*.ts" --include="*.tsx" | grep -v "process.env"
# Find empty vars
grep -E "^[A-Z_]+=\s*$" .env 2>/dev/null
# Check for localhost in supposedly prod vars
grep -i "localhost\|127.0.0.1" .env 2>/dev/null
# Find hardcoded secrets
grep -rn "sk_live\|pk_live\|ghp_\|gho_\|Bearer " src --include="*.ts"
Output
# Environment Report
## Status: [VALID / INVALID]
| Check | Status | Details |
|-------|--------|---------|
| Completeness | PASS/FAIL | X missing vars |
| Security | PASS/FAIL | X exposed secrets |
| Format | PASS/WARN | X format issues |
## Missing Variables
Variables in `.env.example` but not in `.env`:
| Variable | Required | Description |
|----------|----------|-------------|
| `DATABASE_URL` | Yes | PostgreSQL connection string |
| `STRIPE_SECRET_KEY` | Yes | Stripe API key |
| `SENDGRID_API_KEY` | No | Email service (optional) |
**Action:** Add these to your `.env` file
## Security Issues
### ENV-001: Secret Exposed in Code
**Severity:** Critical
**File:** `src/lib/stripe.ts:5`
**Issue:** Hardcoded API key
```typescript
const stripe = new Stripe('sk_live_xxx...'); // EXPOSED
Fix: Use process.env.STRIPE_SECRET_KEY
ENV-002: Secret in Client Bundle
Severity: Critical
File: src/app/page.tsx:12
Issue: Server secret accessible to client
const apiKey = process.env.API_SECRET; // Not NEXT_PUBLIC_ but still exposed
Fix: Only access secrets in server components/API routes
ENV-003: .env Committed to Git
Severity: High
File: .env
Issue: Found .env in git history
Fix:
- Add
.envto.gitignore - Rotate all exposed secrets
- Use
git filter-branchto remove from history
Format Issues
ENV-004: Empty Required Variable
Variable: SMTP_PASSWORD=
Issue: Variable defined but empty
Fix: Set a value or remove if optional
ENV-005: Invalid URL Format
Variable: API_URL=api.example.com
Issue: Missing protocol
Fix: API_URL=https://api.example.com
ENV-006: Development Value in Production
Variable: DEBUG=true
Issue: Debug mode should be off in production
Fix: Set DEBUG=false for production
Undocumented Variables
Variables in .env but not in .env.example:
| Variable | Value (redacted) | Action |
|---|---|---|
LEGACY_API_KEY |
xxx... |
Add to .env.example or remove |
TEST_MODE |
true |
Document purpose |
Environment Template
Required .env.example format:
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 · 169 lines · 20 tokens per session scan A 75ebcea92aa4
env-validator is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,219 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.