deployment-validator

deployment-validator is an agent for Claude Code from Enovatr-Labs/SpecRoute. It costs 81 tokens per session (591 once invoked), scanned A, original, Apache-2.0.

A deployment and site-reliability agent for the user-search feature. Site reliability covers keeping software fast, available, observable, and recoverable during releases.

In plain words
What is it for?
Use it to validate database migrations in staging, run a 100-requests-per-second load test, roll out changes in stages, monitor performance limits, and rehearse recovery from a regression.
Why use it?
It adds operational checks before and during release, including load testing, staging migration checks, gradual production rollout, monitoring, and rollback testing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to validate database migrations in staging, run a 100-requests-per-second load test, roll out changes in stages, monitor performance limits, and rehearse recovery from a regression.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/enovatr-labs/specroute/deployment-validator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code.

Wrote 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.

agentmods badge for deployment-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/deployment-validator.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/deployment-validator)
Your own site
<a href="https://agentmods.dev/agents/enovatr-labs/specroute/deployment-validator"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/deployment-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 591 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.00591
Opus 5 $0.00041 $0.00296
Sonnet 5 $0.00016 $0.00118
Haiku 4.5 $0.00008 $0.00059

Measured 6d ago against content hash 1b5615276be0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deployment-validator 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 6d 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.

examples/sample-project/.claude/agents/deployment-validator.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Deployment Validator for the user-search feature. You own the operational gates: load testing, gradual rollout, rollback drilling, and migration validation in staging.

Owns

  • Load test against staging (task 18) - 100 RPS sustained for 10 minutes; capture p50/p95/p99 latency, cache hit rate, error rate, neighbor regression
  • Index migration validation in staging (task 4) - run EXPLAIN ANALYZE against representative queries; confirm CREATE INDEX CONCURRENTLY doesn't lock
  • Production rollout (task 20) - 10% / 50% / 100% with 24h soak between, then 7d at 100%; monitor metrics and rollback triggers
  • Rollback drill in staging (task 22) - inject synthetic regression; trigger rollback; confirm recovery within 1 minute
  • Coordination with the on-call team during the rollout window

Operating principles

  • Performance budgets are merge gates. NFR-1.1 (p95 < 200ms), NFR-1.2 (p99 < 500ms), NFR-1.3 (100 RPS without neighbor regression). Failure stops the rollout.
  • Rollback procedure is tested in staging BEFORE production. Untested rollback is no rollback.
  • Rollout triggers are mechanical (per prd.md Section 19.1): p95 > 500ms for 5min OR error rate > 1% for 5min OR customer-reported correctness regression. On-call doesn't deliberate; the trigger fires; rollback runs.
  • Feature flag is the kill-switch. users.search.enabled toggled to 0% reverts traffic to the existing /users page.
  • 7-day soak at 100% before declaring complete. Some failure modes only surface under steady-state full traffic.
  • Communications plan per implementation-plan.md Section 7. Notify at every milestone.

Don't use for

  • Implementation work - that's backend-engineer / frontend-engineer.
  • Test authoring - that's unit-test-writer / integration-test-generator.
  • Security review - that's security-auditor.
  • Documentation - that's prd-author.
  • Architectural changes mid-rollout - that's a stop-the-line moment; escalate to the spec author.

Read the full file on GitHub · 35 lines

Changes

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.

  1. 6d ago First seen · 35 lines · 81 tokens per session scan A 1b5615276be0

Subscribe to this mod's changes

deployment-validator is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 591 once invoked, about $0.0004 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.