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 output-securitygit 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/output-security)<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/output-security"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/output-security.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 | $0.00701 |
| Opus 5 | $0.00012 | $0.00351 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Output Security & Secret Scanning 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.
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.
Output Security & Secret Scanning
The pi-guardrails extension automatically scans your tool call results for sensitive data. This prevents accidental exposure of secrets, credentials, and PII in conversation history and logs.
Automatic Enforcement
The output validation handler runs on every tool_result event. When sensitive data is detected:
- Critical findings (AWS keys, GitHub tokens, private keys, database URLs): The content is redacted and a violation is logged.
- Warning findings (generic API keys, JWTs, emails, IP addresses): The content passes through but is flagged in the violation log.
Detected Secret Types
Critical Severity
| Type | Pattern Example |
|---|---|
| AWS Access Key | AKIA... (16 char alphanumeric) |
| AWS Secret Key | aws_secret_access_key = ... |
| GitHub Token | ghp_..., gho_..., ghu_..., etc. |
| GitLab Token | glpat-... |
| Slack Token | xoxb-..., xoxp-..., etc. |
| Stripe Live Key | sk_live_... |
| Private Key | -----BEGIN RSA PRIVATE KEY----- |
| Database URL | postgres://..., mysql://..., mongodb://... |
Warning Severity
| Type | Pattern Example |
|---|---|
| Stripe Test Key | sk_test_... |
| JWT | eyJ... (base64 segments) |
| Generic API Key | api_key = ..., secret = ... |
| Email (if PII enabled) | [email protected] |
| IP Address (if PII enabled) | 192.168.1.1 |
Auto-Redaction
When autoRedact is enabled in config, sensitive values are replaced with [REDACTED] in the tool result you receive. The original value is never stored in logs.
What To Do When Secrets Are Detected
- Do not repeat the secret value in your response
- Warn the user that a secret was exposed in the output
- Suggest rotating the credential immediately
- Log the violation using
guardrail_log_violationwith law "law-3" and severity "critical"
Configuration
{
"outputValidation": {
"enablePII": false,
"autoRedact": true,
"redactionText": "[REDACTED]"
}
}
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 · 78 lines · 24 tokens per session scan A 5fc4307d7e6d
Output Security & Secret Scanning 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 701 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…
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…