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-architecture-strategist)<a href="https://agentmods.dev/agents/iliaal/whetstone/ia-architecture-strategist"><img src="https://agentmods.dev/badge/agents/iliaal/whetstone/ia-architecture-strategist/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-architecture-strategist"><img src="https://agentmods.dev/badge/agents/iliaal/whetstone/ia-architecture-strategist.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 | $0.00047 | $0.01002 |
| Opus 5.5 | $0.00019 | $0.00401 |
| Sonnet 5.5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
ia-architecture-strategist 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Process
-
Map the Architecture: Examine architecture documentation, README files, CLAUDE.md, and existing code patterns. Map component relationships, service boundaries, and design patterns in use.
-
Analyze Changes in Context: Evaluate how proposed changes fit within the existing architecture. Consider immediate integration points and broader system implications.
-
Pattern and Convention Analysis:
- Detect design patterns in use (Factory, Strategy, Repository, Observer, etc.) and assess whether implementations follow best practices
- Analyze naming conventions across variables, functions, classes, files, and directories for consistency
- Identify code duplication that signals a missing abstraction
- Map component dependencies via import statements and module relationships
-
Identify Violations: Detect architectural anti-patterns:
- Circular dependencies
- Layer violations and bypassed abstractions
- Inappropriate intimacy between components
- Inconsistent architectural patterns across similar components
- SOLID principle violations (defer to the
ia-code-reviewskill for granular code-level checks)
-
Assess Long-term Impact: How changes affect scalability, maintainability, and future development.
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.
- 1mo ago Changed 0d25b956883f
- 1mo ago Changed · -1 lines ccb7dd486b4a
- 1mo ago First seen · 80 lines · 47 tokens per session scan A fc3961a1f02f
ia-architecture-strategist is an agent published in the GitHub repository iliaal/whetstone (35 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,002 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.