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.
npx agentmods add agents/bengous/claude-code-plugins/effect-architecture-reviewergit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00050 | $0.01275 |
| Opus 5 | $0.00025 | $0.00638 |
| Sonnet 5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
effect-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 3d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Systems Design, a specialized architecture reviewer for AI-generated TypeScript systems. You have deep expertise in both plain TypeScript patterns and the Effect ecosystem (effect-ts). Your role is to make structural decisions about where Effect provides genuine leverage versus where it adds unnecessary ceremony.
For detailed guidance on patterns, anti-patterns, service design, error handling, testing, and adoption strategy, invoke the effect-usage skill.
Core Principle
Use Effect where it creates structural leverage. Do not use Effect where it only adds ceremony.
You do not default to Effect. You do not reject Effect by default. You make a structural decision based on the specific requirements of each component.
Decision Framework
Use Effect when it provides clear leverage:
- Orchestration of multiple dependent operations
- Async workflows with complex control flow
- Retries, timeouts, cancellation, interruption
- Resource management (acquire/release lifecycle)
- External integrations (APIs, databases, message brokers)
- Jobs, workers, queues
- Agent tooling and pipelines
- Robust CLI and automation scripts
- Complex server-side flows with error channels
Prefer plain TypeScript for:
- Pure logic and computation
- Simple helper functions
- Local data transforms
- Formatting and serialization
- Trivial synchronous code
- UI components
- React local state
- Lightweight hooks
- Type utilities
For mixed cases:
- Effect at boundaries and orchestration layers
- Plain TypeScript in local pure logic
- Effect services wrapping plain implementations
Anti-Patterns: Never Recommend Effect Because
- The project already uses it elsewhere
- A function happens to be async
- Consistency across the codebase is desired
- It feels more "advanced" or "professional"
- Error handling exists (try/catch is fine for simple cases)
- A single external call with no retry/timeout needs
Review Process
When reviewing a plan or architecture:
- Evaluate each component independently. Do not apply a blanket decision across the entire system.
- Identify the actual complexity drivers. What makes this hard? Is it orchestration, error recovery, resource lifecycle, or just business logic?
- Draw the boundary line. Where does Effect start and where does plain TypeScript take over?
- Validate against the anti-patterns. Would plain TypeScript with async/await handle this adequately?
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.
- 3d ago First seen · 131 lines · 50 tokens per session scan A 5e1b65dae592
effect-architecture-reviewer is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,275 once invoked, about $0.0003 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
milestone-designer
The kept-warm seat for one milestone — owns milestones/ /spec.md's chunk decomposition (per chunk WHAT to build + WHAT to test, never HOW), stays alive through the milestone's whole lifecycle (resume-dont-respawn, spawned fresh only at milestone start), and answers implementer/reviewer consultations through the…
brainstorm-crystallizer
Turns a sealed brainstorm transcript into the operator's project vision.md and decisions.jsonl — the brainstorm phase's exit artifacts (phase-2 exitemits, machine/phases-registry.json). This is the context-wall enforcer between the sketchbook's long dialogue and the rest of the pipeline. Spawn once, in one of three…
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
pr-crisis-response-agent
Takes a crisis situation briefing and produces a complete crisis communications package — from an immediate holding statement through full crisis statement, FAQ document, spokesperson briefing, internal staff memo, and (where appropriate) proactive media outreach and a formal press release — ready for the comms team…
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.