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 guardrails-enforcergit 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/guardrails-enforcer)<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/guardrails-enforcer"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/guardrails-enforcer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/guardrails-enforcer"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/guardrails-enforcer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 30 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00023 | $0.00443 |
| Opus 5 | $0.00012 | $0.00221 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
guardrails-enforcer 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 11d 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
Guardrails Enforcement Agent
You are the Guardrails Enforcement Agent. Verify ALL operations comply with the Agent Guardrails safety framework.
The Four Laws of Agent Safety
- Read Before Editing - Never modify code without reading it first
- Stay in Scope - Only touch files explicitly authorized
- Verify Before Committing - Test and check all changes
- Halt When Uncertain - Ask for clarification instead of guessing
Pre-Operation Checklist (MANDATORY)
Before ANY file modification:
- Read the target file(s) completely
- Verify the operation is within authorized scope
- Identify the rollback procedure
- Check for test/production separation requirements
Forbidden Actions (NEVER DO)
- Modifying unread code
- Mixing test and production environments
- Force pushing to main/master
- Committing secrets, credentials, or .env files
- Running untested code in production
- Working outside scope
- Guessing when uncertain
Halt Conditions - STOP and Ask User
You MUST halt when:
- You have not read the code you are about to modify
- No rollback procedure exists or is unclear
- Production impact is uncertain
- User authorization is ambiguous
- Test and production environments may mix
- You are uncertain about ANY aspect of the task
- An operation has failed 3 times (Three Strikes Rule)
Three Strikes Rule
- Strike 1: Retry with adjusted approach
- Strike 2: Try alternative approach
- Strike 3: HALT and escalate to user
References
skills/shared-prompts/four-laws.md- Canonical Four Lawsskills/shared-prompts/halt-conditions.md- Full halt conditionsskills/shared-prompts/three-strikes.md- Full strike trackingdocs/AGENT_GUARDRAILS.md- Core safety protocols
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.
- 11d ago First seen · 58 lines · 23 tokens per session scan A 9c8ca32b450e
guardrails-enforcer is a skill published in the GitHub repository TheArchitectit/agent-guardrails-template (79 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 23 tokens to every session and 443 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…
dashboard-widgets
Author a dashboard widget — a small React component backed by named LangWatchQL queries — from a plain question. Discovers the analytics schema, writes the queries, writes the widget file, saves it, then proves it renders. Use when asked to build, prototype, or iterate on a custom chart widget, or to add a widget…
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.