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 commands/lazorgurl/terror/debug-infragit 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 | $0.00017 | $0.00443 |
| Opus 5 | $0.00009 | $0.00221 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
debug-infra 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
Debug Infrastructure
Systematically diagnose infrastructure issues.
Steps
-
Gather symptoms. Ask the user what they are experiencing:
- Can't connect to a service
- Deployment failed
- Timeouts or high latency
- 5xx errors
- Permission denied
- Resource not found
- Unexpected behavior
-
Identify the affected resource. Call
terror_statusto list resources and ask the user to confirm which resource or service is affected. -
Systematic checks. Based on the symptom, run through the relevant checks in order:
Connectivity issues (can't connect, timeout):
- Check resource health via
terror_health - Verify the resource is running and in the correct state
- Check security groups / firewall rules for the relevant ports
- Verify DNS resolution if a domain is involved
- Check VPC routing and subnet configuration
- Test from the same network context (public vs private)
Permission errors (403, permission denied):
- List IAM bindings on the resource (
gcp_iam_list,aws_iam_list) - Check the service account or role being used
- Verify the required permissions for the operation
- Check for org-level policies or SCPs that might block access
5xx errors:
- Check service health and recent deployments
- Look at resource utilization (CPU, memory, connections)
- Check dependent services (database, cache, external APIs)
- Review recent configuration changes
Deployment failures:
- Check the deployment logs
- Verify the container image or artifact exists
- Check resource quotas and limits
- Verify IAM permissions for the deployment service account
- Check resource health via
-
Hypothesis and resolution. After gathering data:
- State the most likely root cause
- Propose a fix with the specific Terror commands to run
- Use the decision gate before applying any changes
- Verify the fix resolves the issue
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 · 56 lines · 17 tokens per session scan A bece12c7c8f3
debug-infra is a command published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 17 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.