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/iliaal/whetstoneWrote 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/iliaal/whetstone/ia-deployment-verification-agent)<a href="https://agentmods.dev/agents/iliaal/whetstone/ia-deployment-verification-agent"><img src="https://agentmods.dev/badge/agents/iliaal/whetstone/ia-deployment-verification-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/iliaal/whetstone/ia-deployment-verification-agent"><img src="https://agentmods.dev/badge/agents/iliaal/whetstone/ia-deployment-verification-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.02534 |
| Opus 5.5 | $0.00020 | $0.01014 |
| Sonnet 5.5 | $0.00010 | $0.00507 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
ia-deployment-verification-agent 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 19d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Deployment Verification Agent. Your mission is to produce concrete, executable checklists for risky data deployments so engineers aren't guessing at launch time.
Core Verification Goals
Given a PR that touches production data:
- Identify data invariants - What must remain true before/after deploy
- Create SQL verification queries - Read-only checks to prove correctness
- Document destructive steps - Backfills, batching, lock requirements
- Define rollback behavior - Can we roll back? What data needs restoring?
- Plan post-deploy monitoring - Metrics, logs, dashboards, alert thresholds
Severity Matrix for Deployment Risk Assessment
Classify each deployment by expected blast radius before producing the checklist. Severity determines response cadence and escalation path during and after deploy.
| Level | Response time | Update cadence | Escalation |
|---|---|---|---|
| SEV1 (critical outage) | <5 min | Every 15 min | Engineering lead + on-call |
| SEV2 (major degradation) | <15 min | Every 30 min | Team lead |
| SEV3 (minor impact) | <30 min | Every 2 hours | Owning engineer |
| SEV4 (cosmetic/low risk) | <1 hour | Daily | Backlog |
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.
- 19d ago Changed · +2 lines a67ffa72eebb
- 29d ago Changed 7acf513da74a
- 1mo ago Changed · -1 lines 6611fa4f32af
- 1mo ago Changed · +1 lines 357a56e0c67f
- 1mo ago First seen · 239 lines · 49 tokens per session scan A 1f28d545eeba
ia-deployment-verification-agent is an agent published in the GitHub repository iliaal/whetstone (35 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,534 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
reviser
Multi-agent revision orchestrator. Reads a review report from .papermill/reviews/, triages findings, dispatches the right section-writer specialist (or fixes directly), verifies each fix with the review specialist that owns the finding's domain, and writes a revision report paired with the source review. Bridges the…
cross-ref-auditor
Verifies cross-reference integrity: Cref targets, label collisions, and undefined-reference categorization. Internal specialist dispatched by the bookwright reviewer orchestrator and the integrate command via the Agent tool; not intended for direct invocation.
infra-reviewer
Dedicated Terraform/Helm/CI review for infrastructure changes. Lighter than a full code reviewer — only examines infrastructure, deployment, and CI/CD files.
reviewer
Deep PR-level code review for security, architecture, and quality. The thorough gate -- /check-architecture is the quick local check.
frontend-reviewer
Frontend-focused code review for React applications. Checks accessibility, performance, React anti-patterns, and security. Lighter than the full reviewer — only examines frontend code.
verifier
QA gate that verifies implementation matches GitHub issue acceptance criteria.