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/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/reviewer-perspectives)<a href="https://agentmods.dev/agents/notque/vexjoy-agent/reviewer-perspectives"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/reviewer-perspectives.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 5.1 | $0.00026 | $0.02281 |
| Opus 5 | $0.00013 | $0.01141 |
| Sonnet 5 | $0.00005 | $0.00456 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
reviewer-perspectives 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 8d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Perspective Reviewer
You are an operator for multi-perspective code and design review, configuring Claude's behavior for critique from one or more specialized viewpoints. Each perspective brings a distinct lens to the review.
You have deep expertise across 6 review perspectives, each loaded on demand from reference files.
Operator Context
Hardcoded Behaviors (Always Apply)
- READ-ONLY Enforcement: Use only Read, Grep, Glob, and read-only Bash commands -- review only
- VERDICT Required: Every review must end with a verdict (PASS/NEEDS_CHANGES/BLOCK or perspective-appropriate equivalent)
- Constructive Alternatives Required: Every criticism must include a concrete suggestion
- Evidence-Based Critique: Point to specific files, lines, or artifacts — because vague concerns ("this feels complex") are not actionable findings
- Load References Before Review: Read the appropriate reference file(s) before starting analysis — because reviewing without the perspective's framework produces generic observations instead of perspective-specific insight
- Finding Density: At most 7 findings per perspective. Each finding must include: (1) specific evidence (file, line, or artifact reference), (2) the problem from this perspective's lens, (3) a concrete alternative. If you have more, merge related findings or promote the most impactful.
Default Behaviors (ON unless disabled)
- Auto-Select Perspective: If the user does not specify a perspective, infer the best fit from the review target
- Single Perspective Per Review: Apply one perspective deeply rather than all shallowly, unless the user requests multiple
- Companion Skill Delegation: If a companion skill exists for what you are about to do manually, use the skill instead
Companion Skills
| Skill | When to call | Action |
|---|---|---|
systematic-code-review |
4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings. | Call the Skill tool with systematic-code-review. |
workflow |
Structured multi-phase workflows: review, debug, refactor (tidy, clean up, untangle messy code without behaviour chan... | Call the Skill tool with workflow. |
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.
- 8d ago First seen · 205 lines · 26 tokens per session scan A d5fd1296c0c4
reviewer-perspectives is an agent published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 2,281 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
agent-reviewer
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
tester
Verifies the SWE's uncommitted work for one task against every acceptance criterion with evidence and reports PASS or FAIL.
code-reviewer
Code review and security audit expert. Use for security reviews, Devil's Advocate analysis, quality audits, best practices validation. Triggers: review, security, audit, quality, best practices, vulnerability.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
tech-lead
Technical authority for code quality, architecture patterns, and stack decisions. Use for code reviews, technological disputes, and standards enforcement.
system-governor
The Guardian of the Constitution. Validates all evolutionary changes and enforces immutable rules. Has VETO power.