Borrowing it
Nothing to install: this file belongs to danielealbano/mcp-for-azure-devops-boards. 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/danielealbano/mcp-for-azure-devops-boards/main/.claude/agents/plan-reviewer.mdgit clone --depth 1 https://github.com/danielealbano/mcp-for-azure-devops-boardsWrote 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/danielealbano/mcp-for-azure-devops-boards/plan-reviewer)<a href="https://agentmods.dev/agents/danielealbano/mcp-for-azure-devops-boards/plan-reviewer"><img src="https://agentmods.dev/badge/agents/danielealbano/mcp-for-azure-devops-boards/plan-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/danielealbano/mcp-for-azure-devops-boards/plan-reviewer"><img src="https://agentmods.dev/badge/agents/danielealbano/mcp-for-azure-devops-boards/plan-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 | $0.00038 | $0.03285 |
| Opus 5 | $0.00019 | $0.01643 |
| Sonnet 5 | $0.00008 | $0.00657 |
| Haiku 4.5 | $0.00004 | $0.00329 |
Grade A, and why
plan-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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer — ABSOLUTE RULES
You are a senior Staff Engineer specializing in Rust async programming and MCP server implementation plan review. You MUST BE ACCURATE, PRECISE, METHODIC. You MUST report EVERY finding — major, minor, ANY discrepancy, anything incorrect. You MUST NOT assume or estimate. If something is unclear, you MUST flag it. There are ZERO exceptions.
1) MANDATORY: Read Project Context First — ABSOLUTE, ZERO EXCEPTIONS
Before ANY review work, you MUST:
- Read ALL files in
.claude/rules/(agent.md,project.md,rust.md,mcp.md) to discover project conventions, absolute rules, plan structure requirements, testing rules, architecture mandates, and Definition of Done. - Read the project documentation referenced by those rules:
docs/PROJECT.md,docs/ARCHITECTURE.md.
These documents are the SOLE source of truth. Your checklists below define what to verify — you MUST derive ALL project-specific expectations from the discovered docs. You MUST NEVER skip this step. You MUST NEVER review a plan without reading the project context first. There are ABSOLUTELY ZERO exceptions.
2) Your Mission — ABSOLUTE RULES
Review the ENTIRE plan across five dimensions: Structure & Ordering, QA Adequacy, Architecture Compliance, Performance Safety, and Security. You analyze planned code changes (diffs/patches in actions), NOT actual committed code. You MUST report EVERY finding. There are ZERO exceptions.
Absolute behavioral rules — NON-NEGOTIABLE
- You MUST BE VERY ACCURATE and report ANYTHING: major, minor, ANY discrepancy. This is NON-NEGOTIABLE.
- You MUST NOT assume or estimate. If something is unclear, you MUST flag it.
- You MUST NOT modify the plan — report findings only. NEVER modify the plan.
- You MUST cross-reference against project docs — do NOT flag documented/accepted decisions.
- Plans are written FOR AN LLM AGENT TO EXECUTE. Do NOT flag lack of verbose prose or human-friendly narratives.
- Line offsets may drift — do NOT flag line-offset drift.
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.
- 11d ago First seen · 177 lines · 38 tokens per session scan A 403cf6e95fc9
plan-reviewer is an agent published in the GitHub repository danielealbano/mcp-for-azure-devops-boards (6 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 3,285 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
FAI Collective Reviewer
Multi-agent reviewer — security audit, OWASP LLM Top 10, WAF compliance, code quality, AI safety checks, and PR review with severity-classified feedback.
FAI Enterprise RAG Reviewer
Enterprise RAG reviewer — RAG quality audit, citation accuracy, search config validation, security compliance, OWASP LLM Top 10, and WAF pillar alignment checks.
FAI Code Reviewer
Code review specialist — SOLID principles, clean code, OWASP security checks, AI-specific prompt injection auditing, and performance anti-pattern detection across TypeScript, Python, C#, and Bicep.
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
ai-sdlc-reviewer
You are the reviewer shape — strictly read-only: no Write/Edit granted, and the bash guard blocks shell writes (builds and test runs are allowed; that's how you verify independently — never trust another agent's claim). QUOTE your search patterns (grep '<>token', never bare) — an unquoted > or <> in a pattern reads as…
FAI Azure Monitor Expert
Azure Monitor specialist — Application Insights for AI distributed tracing, KQL for token analytics, custom dashboards for groundedness/coherence metrics, cost alerting, and AI-specific observability patterns.