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 policy-configgit 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/policy-config)<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/policy-config"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/policy-config/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/policy-config"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/policy-config.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00696 |
| Opus 5 | $0.00009 | $0.00348 |
| Sonnet 5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Policy Configuration Hierarchy 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy Configuration Hierarchy
Guardrail policies are loaded from three layers, with later layers overriding earlier ones via deep merge. This allows organizations to set baseline rules, teams to tighten them, and projects to customize further.
Three Policy Layers
| Layer | Location | Priority | Typical Use |
|---|---|---|---|
| Organization | ~/.pi/guardrails-org.json or PI_GUARDRAILS_ORG_CONFIG |
Lowest (base) | Company-wide defaults, compliance requirements |
| Team | ~/.pi/teams/{name}/guardrails.json or PI_GUARDRAILS_TEAM={name} |
Middle | Team-specific rules, project-type constraints |
| Project | {cwd}/.pi-guardrails.json or {cwd}/.pi/guardrails.json |
Highest | Per-project customization, local overrides |
Deep Merge Behavior
Later layers deep-merge into earlier layers:
- Primitive values: Later layer wins (
"maxStrikes": 5overrides"maxStrikes": 3) - Objects: Merged recursively (team can add keys without losing org defaults)
- Arrays: Later layer replaces earlier array entirely (not concatenated)
Example:
// Organization: ~/.pi/guardrails-org.json
{
"maxStrikes": 3,
"toolPermissions": { "tools": { "bash": "ask" } },
"outputValidation": { "autoRedact": true }
}
// Team: ~/.pi/teams/backend/guardrails.json
{
"maxStrikes": 5,
"toolPermissions": { "tools": { "bash": "auto" } }
}
// Merged result for backend team:
{
"maxStrikes": 5, // team overrides org
"toolPermissions": {
"tools": { "bash": "auto" } // team overrides org
},
"outputValidation": { "autoRedact": true } // inherited from org
}
Environment Variables
| Variable | Purpose |
|---|---|
PI_GUARDRAILS_ORG_CONFIG |
Override org config file path |
PI_GUARDRAILS_TEAM |
Team name to load team policy |
What This Means For You
- Check
guardrail_statusat session start to see the effective configuration - Do not assume defaults — your organization may have stricter rules
- Respect the hierarchy — if a tool is blocked at org level, a project override does not unblock it (unless the project policy explicitly does so)
- When uncertain, default to the stricter interpretation
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.
- 10d ago First seen · 78 lines · 17 tokens per session scan A 872a64cbceed
Policy Configuration Hierarchy is a skill published in the GitHub repository TheArchitectit/agent-guardrails-template (79 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 17 tokens to every session and 696 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
construction-expert
Expert-level construction management, project planning, BIM, safety compliance, and construction technology. Use when the user mentions BIM, project management, safety, or building, or when the task involves Construction Management, Technologies, Standards and Regulations, or Cost Control.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
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…
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…