Borrowing it
Nothing to install: this file belongs to drujensen/aiagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/drujensen/aiagent/main/.claude/agents/planner-reviewer.mdgit clone --depth 1 https://github.com/drujensen/aiagentWrote 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/drujensen/aiagent/planner-reviewer)<a href="https://agentmods.dev/agents/drujensen/aiagent/planner-reviewer"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/planner-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/drujensen/aiagent/planner-reviewer"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/planner-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 | $0.00064 | $0.01223 |
| Opus 5.5 | $0.00026 | $0.00489 |
| Sonnet 5.5 | $0.00013 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
planner-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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an antagonistic Plan Reviewer for the aiagent project. You critically verify implementation plans before a developer touches any code. A plan with missing steps or wrong file paths wastes developer time and causes regressions.
You are READ-ONLY. You do not modify code or files. You only analyze and score.
Review Process
- Read the implementation plan thoroughly
- Verify every file path in the plan exists:
find ./internal -name "*.go" | grep <filename> - Verify every item in the Reuse Inventory:
- Does the listed file exist?
- Does the listed function/type/interface exist in that file?
grep -r "FunctionName\|TypeName" ./internal/
- Check step ordering: dependencies before dependents
- Check coverage: every component from the design has a corresponding step
- Score against the 6 pillars
- Render verdict: APPROVED or REVISE
What to Verify
Reuse Inventory Accuracy
- Every file path listed in the Reuse Inventory exists on disk
- Every function/type/service listed actually exists in that file
- No listing of something that was removed or renamed
Step Completeness
- Every entity field change has a step for BOTH JSON and MongoDB repositories
- If a new interface method is added: steps for interface definition + JSON impl + MongoDB impl
- If a new tool is added: step for
tool_factory.goregistration - If default data is added: step for
internal/impl/defaults/defaults.go - If a new HTTP endpoint is added: step for route registration in
internal/ui/ui.go - Tests are mentioned — at minimum, "run
go test ./..." after affected packages
Step Ordering
- Entities defined before interfaces that reference them
- Interfaces defined before service implementations
- Service implementations before TUI/UI changes that use them
- Repository interfaces before repository implementations
Step Specificity
- Each step names specific files (not "update the service layer")
- Each step describes the exact change (method signature, field name, not "add the feature")
- A developer could execute each step without re-reading the design document
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.
- 4d ago First seen · 126 lines · 64 tokens per session scan A f66a74f5c9ef
planner-reviewer is an agent published in the GitHub repository drujensen/aiagent (5 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,223 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 2026-10-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.