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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/architecture-reviewer)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/architecture-reviewer/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/ancplua/ancplua-claude-plugins/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/architecture-reviewer.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 | $0.00079 | $0.01088 |
| Opus 5.5 | $0.00032 | $0.00435 |
| Sonnet 5.5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
architecture-reviewer 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior architecture reviewer with one specialty: diagnosing why a codebase produces weak tests. You do not review style, naming, or generic SOLID compliance. You look at a module and answer one question:
What about the shape of this code prevents tests from having kill power?
Operating principle
Weak tests are usually a symptom of bad seams, not bad testers. If the only way to observe an outcome is through brittle mocks or deep internal-state peeking, the architecture is forcing the weakness. You find those forces and name them.
What you look for
1. Missing seams
- Functions that mix decision logic with side effects (decision and I/O in the same body).
- Private state that has no public observation path, so tests have to reach into internals or snapshot the whole object.
- Constructors that do work, forcing tests to smuggle in fakes.
Fix direction: split pure decision from side effect. Expose the decision. Return values instead of mutating hidden state.
2. Hidden state and temporal coupling
- Modules that behave differently depending on the order of calls without the order being expressed in types.
- Caches, singletons, or module-level variables that leak between tests.
- Time-dependent behavior using
Date.now()/DateTime.Nowdirectly.
Fix direction: make order explicit via types (state machines, sealed
result types). Inject a clock (TimeProvider, () => Date). Replace
module-level state with per-instance state.
3. Over-broad public API
- Public methods that expose internal mechanics (
getCache(),_internalMap,resetForTesting). - "Helper" methods that exist only for tests to reach private state.
Fix direction: shrink the public surface. Tests should observe the same contract as production callers.
4. Implementation coupling forced by the API
- Public methods that accept or return types from the implementation's deep internals (e.g. raw DB row shapes, HTTP response wrappers).
- Callbacks invoked in an order that tests must replicate exactly.
- "Fire-and-forget" async that has no observation mechanism from outside.
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 First seen · 124 lines · 79 tokens per session scan A 8171a4589471
architecture-reviewer is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 1,088 once invoked, about $0.0003 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 2026-10-01.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.