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 tool-permissionsgit 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/tool-permissions)<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/tool-permissions"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/tool-permissions/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/tool-permissions"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/tool-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00590 |
| Opus 5 | $0.00012 | $0.00295 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
Tool Permission Control 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Permission Control
The pi-guardrails extension enforces tool-level permissions. Before any tool call executes, the permission handler checks whether the tool is allowed, requires confirmation, or is blocked.
Automatic Enforcement
The permission handler runs on every tool_call event before execution:
- auto: Tool executes immediately (no confirmation needed)
- ask: Tool execution is paused and you must ask the user for approval
- blocked: Tool execution is refused with reason
Default Permission Matrix
| Tool | Level | Rationale |
|---|---|---|
| bash | ask | Shell commands can be destructive |
| write | auto | File creation is scoped to write paths |
| edit | auto | Edits are guarded by scope + read tracking |
| read | auto | Reading is always safe |
| grep | auto | Search is always safe |
| glob | auto | File listing is always safe |
| ls | auto | Directory listing is always safe |
When You Need Confirmation
If a tool is set to ask level:
- Stop before executing the tool
- Explain to the user what the tool will do
- Ask "Should I proceed with [tool] to [action]?"
- Wait for explicit approval
- Execute only after approval — do not assume consent
Session Overrides
Permissions can be adjusted within a session via guardrail_mcp with action set_permission:
action: set_permission
toolName: bash
level: auto
reason: User approved bash for this task
This sets the override for the remainder of the session only.
Configuration
Permissions are configured in .pi-guardrails.json:
{
"toolPermissions": {
"defaultLevel": "auto",
"tools": {
"bash": "ask",
"write": "auto",
"edit": "auto",
"read": "auto"
}
}
}
Organization and team policies can override these defaults — see [[policy-config]].
What To Do When Blocked
- Do not retry the blocked tool call
- Inform the user which tool was blocked and why
- Suggest an alternative approach that uses allowed tools
- If the block seems incorrect, suggest the user update their permission configuration
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 · 87 lines · 23 tokens per session scan A b9df37ab6013
Tool Permission Control is a skill published in the GitHub repository TheArchitectit/agent-guardrails-template (79 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 23 tokens to every session and 590 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…
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…
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…