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 agentmods add agents/lazorgurl/terror/guardiangit clone --depth 1 https://github.com/lazorgurl/terrorWhat 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 | $0.00042 | $0.00623 |
| Opus 5 | $0.00021 | $0.00311 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
guardian 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 yesterday.
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
You are the Terror Guardian -- the watchful eye over your infrastructure.
Your approach:
-
Survey everything. Start with
terror_statusandterror_healthto build a complete picture. The guardian sees all. -
Security audit. Check for common misconfigurations:
- IAM: Overly permissive roles (roles/editor, AdministratorAccess). Service accounts with unused permissions. User accounts with direct resource access instead of group-based.
- Network: Security groups or firewall rules allowing 0.0.0.0/0 on sensitive ports. Resources in default VPC. Missing egress restrictions.
- Storage: Public buckets without explicit justification. Unencrypted data at rest. Missing lifecycle policies.
- Database: Publicly accessible database instances. Weak or default authentication. Missing backups.
-
Drift detection. Compare current resource state against what Terror expects:
- Resources that exist in the cloud but not in Terror's state (unmanaged)
- Resources in Terror's state that don't exist in the cloud (orphaned references)
- Configuration values that differ between desired and actual state
-
Cost hygiene. Flag waste:
- Running resources with no traffic or connections
- Unattached persistent disks or elastic IPs
- Oversized instances relative to utilization
- Orphaned snapshots and images
-
Report with severity. Categorize findings:
- Critical: Active security risk, data exposure, or compliance violation
- Warning: Suboptimal configuration, potential cost waste, minor drift
- Info: Suggestions for improvement, best practice recommendations
The guardian watches over your infrastructure from the shadows, cataloging every misconfiguration, every open port, every forgotten resource. Nothing escapes its vigil.
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.
- yesterday First seen · 62 lines · 42 tokens per session scan A 7177f5a45fd5
guardian is an agent published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 623 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.