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/nometria/claude-code-plugin/previewgit clone --depth 1 https://github.com/nometria/claude-code-pluginWhat 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 | $0.00011 | $0.00478 |
| Opus 5 | $0.00005 | $0.00239 |
| Sonnet 5 | $0.00002 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
preview scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl:*), Bash(cat:*), Bash(grep:*), Bash(echo:*), Read What it actually says
Deploy Staging Preview
You are creating a temporary staging preview of the user's app. This is free and creates a short-lived URL.
Step 1: Resolve token
TOKEN="${NOMETRIA_API_KEY:-${NOMETRIA_TOKEN:-$(grep -s 'NOMETRIA_API_KEY\|NOMETRIA_TOKEN' .env .env.local 2>/dev/null | head -1 | cut -d= -f2- | tr -d ' "'"'"'')}}"
echo "Token found: $([ -n "$TOKEN" ] && echo 'yes' || echo 'no')"
If no token: tell the user to run nom login or /nometria-login and stop.
Step 2: Identify the app
# Try workspace config first
cat nometria.json 2>/dev/null
If no nometria.json, list migrations:
curl -s -X POST https://app.nometria.com/listUserMigrations \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOKEN" \
-d '{}'
Pick the correct migration. If $ARGUMENTS was provided, match by app name. Otherwise, if multiple exist, ask the user. Store MIGRATION_ID.
Step 3: Deploy preview
curl -s -X POST https://app.nometria.com/deployStagingPreview \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOKEN" \
-d "{\"migration_id\": \"$MIGRATION_ID\", \"production\": false}"
Step 4: Report result
Parse the response. On success, display:
🔗 Preview deployed!
URL: <preview_url>
Expires: ~2 hours
This is a temporary preview. Use /deploy for production.
On failure, show the error message and suggest checking the dashboard.
Execute all curl commands and report the results.
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 · 63 lines · 11 tokens per session scan A bf615c225d20
preview is a command published in the GitHub repository nometria/claude-code-plugin (3 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 478 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.