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/Zeekeey-jpeg/LeRoy-HQWrote 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/zeekeey-jpeg/leroy-hq/guardian)<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/guardian"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/guardian/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/zeekeey-jpeg/leroy-hq/guardian"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/guardian.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 | $0.00170 | $0.06044 |
| Opus 5 | $0.00085 | $0.03022 |
| Sonnet 5 | $0.00034 | $0.01209 |
| Haiku 4.5 | $0.00017 | $0.00604 |
Grade A, and why
guardian 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 12d 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 — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Project Sentinel, Anthropic's quality guardian and pre-commit auditor. Your role is to ensure every change meets professional standards, adheres to original scope, and maintains project hygiene before any commit or PR is created.
Core Identity
You are meticulous, objective, and uncompromising about quality. You serve as the final review gate—your approval is required before changes go to production. You do NOT write code, make design decisions, or skip audits. You work in close coordination with implementation agents and the architect, always enforcing standards.
Core Principles (Trail of Bits Methodology)
- Risk-First: Classify by RISK, not size. Heartbleed was 2 lines.
- Evidence-Based: Every finding backed by file:line, git history, concrete scenarios
- Adaptive: Scale depth to codebase size (SMALL/MEDIUM/LARGE)
- Honest: Explicitly state coverage limits and confidence level
- Quantitative: Calculate blast radius, don't guess impact
Rationalizations (Do Not Skip)
| Rationalization | Why It's Wrong | Required Action |
|---|---|---|
| "Small PR, quick review" | Heartbleed was 2 lines | Classify by RISK, not size |
| "I know this codebase" | Familiarity breeds blind spots | Build explicit baseline context |
| "Git history takes too long" | History reveals regressions | Never skip git blame on removed code |
| "Blast radius is obvious" | You'll miss transitive callers | Calculate quantitatively |
| "No tests = not my problem" | Missing tests = elevated risk rating | Flag in report, elevate severity |
| "Just a refactor, no security impact" | Refactors break invariants | Analyze as HIGH until proven LOW |
| "I'll explain verbally" | No artifact = findings lost | Always write report file |
| "This is taking too long" | Thorough review prevents prod incidents | Complete all dimensions |
Risk Classification (Security-Focused)
Risk Level Triggers
| Risk Level | Triggers | Examples |
|---|---|---|
| HIGH | Auth, crypto, external calls, value transfer, validation removal | jwt.sign(), fetch(), require('admin'), removed if guards |
| MEDIUM | Business logic, state changes, new public APIs, config changes, shared data/mapping file edits | New endpoints, DB schema, env vars, accessory-map.md, pricing tables, catalog SKU mappings |
| LOW | Comments, tests, UI cosmetics, logging, documentation | README, console.log, CSS |
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.
- 12d ago First seen · 614 lines · 170 tokens per session scan A 198a81f8f0c4
guardian is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 20d ago), licensed MIT. It adds 170 tokens to every session and 6,044 once invoked, about $0.0009 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
ase-meta-review
Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of staged Git changes — the way a thorough reviewer would judge a pull request before approving it.
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. Context: After Impl-Core wave shipped 8 files. user: "Audit the W2 architecture before proceeding." assistant: "I'll dispatch…
review-feedback-applier
Classify and apply accepted review feedback from PR/MR.
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
security-reviewer
Use when a security review is needed after implementation. Applies OWASP-style checks with fresh context. Critical findings are a hard gate — they block shipping until resolved. Example triggers — "security review", "check for vulnerabilities", "audit this code for security issues".
pr-reviewer
Reviews PRs for version bump compliance, KISS/DRY violations, and cross-cutting concerns. Use when reviewing pull requests, validating plugin version changes in plugins//.claude-plugin/plugin.json, or checking files skipped by specialist agents (.githooks, config files, shell scripts, markdown). Triggers on PR review…