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 TheArchitectit/agent-guardrails-template --skill env-separatorgit clone --depth 1 https://github.com/TheArchitectit/agent-guardrails-templateWrote 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/thearchitectit/agent-guardrails-template/env-separator)<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/env-separator"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/env-separator.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 | $0.00024 | $0.00291 |
| Opus 5 | $0.00012 | $0.00146 |
| Sonnet 5 | $0.00005 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
env-separator 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.
What it actually says
Environment Separator Agent
Enforce strict separation between test and production environments.
The Three Laws of Environment Separation
- Production Code First - Production code MUST be created before test code
- Separate Instances - Test and production MUST use separate service instances
- No Data Mixing - Test data must NEVER contaminate production databases
Pre-Flight Checklist
Before creating test code or running tests:
- Production implementation exists and is functional
- Test environment uses separate database/service instances
- Test data will not leak to production
- Separate user accounts for test vs production
Forbidden Patterns (NEVER ALLOW)
- Tests writing to production databases
- Test fixtures in production code paths
- Shared database instances
- Test credentials in production configs
- Production data in tests without sanitization
When Uncertain
If you cannot verify environment separation:
- HALT the operation immediately
- Ask the user to confirm environment boundaries
- Do NOT proceed until separation is guaranteed
References
docs/standards/TEST_PRODUCTION_SEPARATION.md- Full environment rulesskills/shared-prompts/production-first.md- Production-first mandate
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 · 43 lines · 24 tokens per session scan A 5c4c2e00baed
env-separator is a skill published in the GitHub repository TheArchitectit/agent-guardrails-template (79 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 24 tokens to every session and 291 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
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
agent-improve
Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that…
test-compliance
Test that your AI agent stays observational and doesn't give prescriptive advice in regulated domains (healthcare, finance, legal). Creates scenario tests for boundary enforcement and red team tests for adversarial probing. Use when your agent advises but must not prescribe.
trulens-blocking-guardrails
Configure and use feedback functions as runtime blocking guardrails.