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/setupgit 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 | $0.00016 | $0.00982 |
| Opus 5 | $0.00008 | $0.00491 |
| Sonnet 5 | $0.00003 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade B, and why
setup scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json` and merge these keys into the existing JSON (do not overwrite other keys): How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terror Setup
Walk the user through configuring Terror for their project. They should never have to manually edit config files.
Step 1: Welcome + detect existing config
Check if .mcp.json already has a terror entry and if ~/.terror/credentials.json exists. If Terror is already configured, tell the user what's set up and ask if they want to reconfigure or add a provider.
If Terror source isn't installed at ~/.terror/src, install it:
git clone https://github.com/lazorgurl/terror.git ~/.terror/src
cd ~/.terror/src && bun install && bun run build
Step 2: Choose providers
Use the AskUserQuestion tool:
Question: "Which cloud providers do you want to manage with Terror?"
- GCP — Google Cloud Platform (full CRUD support)
- AWS — Amazon Web Services (coming soon — read-only)
- Cloudflare — Cloudflare Workers, DNS, R2 (coming soon — read-only)
- DigitalOcean — Droplets, Spaces, Apps (coming soon — read-only)
Allow multi-select.
Step 3: Configure each selected provider
For each provider the user selected, ask provider-specific questions using AskUserQuestion:
GCP
Terror uses Application Default Credentials (ADC) automatically. Check if the user is already authenticated:
gcloud auth application-default print-access-token 2>/dev/null && echo "ADC OK" || echo "NOT AUTHENTICATED"
If not authenticated, run:
gcloud auth application-default login
Then ask using AskUserQuestion:
- "Which GCP project should Terror manage?" — Free text. If they're unsure, run
gcloud projects listto show their projects and let them pick. - "Which GCP region?" — Options: us-central1, us-east1, us-west1, europe-west1, asia-east1, or Other.
If the user wants to use a service account key instead, set GOOGLE_APPLICATION_CREDENTIALS in the .mcp.json env pointing to the key file.
AWS (when available)
- Authentication method: SSO, access keys, or IAM role
- Default region
- Account ID
Cloudflare (when available)
- API token
- Account ID
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 · 131 lines · 16 tokens per session scan B 465cde89952c
setup is a command published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 982 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.