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.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRouteWrote 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.
[](https://agentmods.dev/agents/enovatr-labs/specroute/deployment-validator)<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>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.
| Model | Per session | Once 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 |
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.
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 ANALYZEagainst representative queries; confirmCREATE INDEX CONCURRENTLYdoesn'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.mdSection 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.enabledtoggled to 0% reverts traffic to the existing/userspage. - 7-day soak at 100% before declaring complete. Some failure modes only surface under steady-state full traffic.
- Communications plan per
implementation-plan.mdSection 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.
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.
- 6d ago First seen · 35 lines · 81 tokens per session scan A 1b5615276be0
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.
Other agents, from other repositories
graph-verifier
A validation agent for this pattern's output.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
ux-evaluator
Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
cloud
Use when designing cloud infrastructure, setting up IaC, configuring serverless functions, or planning cloud architecture.