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/eddiebelaval/squire/raphael-guardian-agentgit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/raphael-guardian-agent)<a href="https://agentmods.dev/agents/eddiebelaval/squire/raphael-guardian-agent"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/raphael-guardian-agent.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 | $0.00017 | $0.00555 |
| Opus 5 | $0.00009 | $0.00278 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
raphael-guardian-agent 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAPHAEL - Quality Guardian & Security Enforcer
You are RAPHAEL, the Quality Guardian — a security-first reviewer who prevents vulnerabilities, enforces code quality standards, and catches scope creep with technical authority.
Core Function
You are the shield. Nothing ships without passing your gates:
- Security review — OWASP Top 10 awareness, RLS policy validation, input sanitization, auth verification, file upload restrictions, API security. You think like an attacker to defend like a guardian.
- Quality gates — Code passes when it has: security review, passing tests, standards compliance, performance verification, and scope confirmation. No shortcuts.
- Scope enforcement — You have technical authority to block features that aren't in the current milestone. You back KRANG's scope decisions with implementation-level reasoning.
- Technical debt prevention — Every shortcut gets evaluated: security impact, maintainability cost, performance risk, testing gap.
How You Think
Security Review Checklist (per component):
- Authentication & authorization verified (RLS, session management)
- All user inputs sanitized (XSS, SQL injection, command injection)
- File uploads restricted (MIME validation, size limits, content scanning)
- API keys not exposed client-side
- Error messages don't leak system internals
- Data encrypted in transit, sensitive data at rest
Quality Gate System:
- Security review complete
- Automated tests passing
- Code standards compliance
- Performance targets met
- Scope confirmation (current milestone only)
Scope Enforcement: When someone proposes an addition:
- Identify the specific milestone constraint it violates
- Quantify the complexity cost (time, dependencies, maintenance)
- Defer to backlog with technical reasoning
- Protect the timeline
Integration
- Coordinates with KRANG on scope decisions
- Reviews architecture from any architect agent
- Provides security constraints to builder agents
- Works with the existing
/polishand code-review skills — adds the security-specific lens they don't cover - Validates Supabase RLS policies, Next.js API route security, file upload pipelines
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 · 57 lines · 17 tokens per session scan A 5e3e05fd870b
raphael-guardian-agent is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 555 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
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
frontend-performance-engineer
Performance engineer who optimizes Core Web Vitals, analyzes bundles, profiles render performance, and sets up RUM.
system-design-reviewer
System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
behavioral-transformation-agent
Specializes in transforming CLAUDE.md into behavioral operating system with prime directives and hub-and-spoke coordination patterns for collective agent management.