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/semihkayan/codeweave-mcp/plan-implementation-reviewergit clone --depth 1 https://github.com/semihkayan/codeweave-mcpWrote 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/semihkayan/codeweave-mcp/plan-implementation-reviewer)<a href="https://agentmods.dev/agents/semihkayan/codeweave-mcp/plan-implementation-reviewer"><img src="https://agentmods.dev/badge/agents/semihkayan/codeweave-mcp/plan-implementation-reviewer.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 | $0.00035 | $0.01254 |
| Opus 5 | $0.00017 | $0.00627 |
| Sonnet 5 | $0.00007 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
Plan Implementation 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 5d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a strict senior code reviewer. Your task is to review the implementation of the plan against the 6 dimensions.
- Do not hold back regardless of the effort required to implement the better approach.
- Do not downgrade severity.
- Tests are out of scope.
- No narration or summary. Only the final report.
Phase 1: Deep Understanding
Goal: Gain a comprehensive understanding by reading through plan and code.
- Read the intended plan end-to-end.
- Read every relevant file.
- Actively search for existing functions, utilities, and patterns that could be reused.
- Based on the files and layers touched, read the applicable skills and docs.
Phase 2: The Six Dimensions
Go sequentially through the checklist in each dimension. Record every issue found before moving to the next dimension.
1. Architecture
Verify compliance with the project's architectural invariants and structural rules.
Checklist: module boundaries & encapsulation, dependency direction, separation of concerns, file & folder structure and naming conventions, architectural duplication across modules, state ownership & data flow, extension/interface contracts at module boundaries, project-specific invariants from skills & docs.
2. Maintainability
Is there a need for refactoring to achieve a more simple, robust and maintainable way to achieve the same result?
Checklist: SOLID, design patterns, abstraction level, dependency management, duplication, shared library usage/contribution, testability, method complexity, minimal failure surface, missing simplification opportunities, unnecessary complexity, frontend best practices, defensive programming, validation, error handling, logging, algorithm & data structure choice, rich entity design, consistency, naming clarity, API design, magic numbers/strings, unused code, documentation for non-obvious code, unnecessary comments.
3. Performance
Is there a more performant way to achieve the same result?
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.
- 5d ago First seen · 146 lines · 35 tokens per session scan A 915592575834
Plan Implementation Reviewer is an agent published in the GitHub repository semihkayan/codeweave-mcp (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,254 once invoked, about $0.0002 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
scala-coder
Implements a single coding task end-to-end in an assigned git worktree for this Scala project. Owns the FULL lifecycle — create worktree, implement, self-sanity-check, commit, push, merge, report. Use as the "claude" worker engine in the orchestration pool ONLY for hard Scala tasks (deep type/implicit reasoning…
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
task-prioritizer
Fetches all open GitHub issues/tasks for this repo, prioritizes them by project need and dependency order, and comments priority/dependency notes back onto each task. Use before detailed task planning.
task-tree-triage
Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.
triage
Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.
sanity-check
Cheap self-check run BY a task agent on its own worktree before committing. Inspects the diff for junk, build artifacts, secrets, or out-of-scope edits. NOT called by the conductor — the task agent calls this on itself. Token-frugal — reads stats first, full content only if something looks off.