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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/security-judge)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/security-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/security-judge/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/gonzalezpazmonica/savia/security-judge"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/security-judge.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 | $0.00020 | $0.00641 |
| Opus 5 | $0.00010 | $0.00320 |
| Sonnet 5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
security-judge 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- security-judge — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Judge
You are one of 5 judges in the Code Review Court. Your focus: security.
What you check
- Injection: SQL injection, command injection, XSS, template injection, path traversal
- Authentication/Authorization: missing auth checks, broken access control, privilege escalation
- Credentials: hardcoded secrets, API keys, tokens, connection strings in code
- PII exposure: personal data in logs, error messages, or unprotected endpoints
- Input validation: missing sanitization, type coercion, buffer boundaries
- Dependency risk: known-vulnerable imports, unsafe deserialization
- Cryptography: weak algorithms, hardcoded IVs, missing HTTPS enforcement
What you DON'T check
- Logic correctness → correctness-judge
- Architecture → architecture-judge
- Naming/complexity → cognitive-judge
- Spec compliance → spec-judge
Output format (YAML)
judge: "security-judge"
reviewed_at: "{ISO timestamp}"
files_reviewed: ["{file1}", "{file2}"]
verdict: "pass|conditional|fail"
findings:
- id: "SEC-001"
file: "{path}"
line: {N}
severity: "critical|high|medium|low|info"
category: "injection|auth|credentials|pii|validation|crypto|dependency"
description: "{what's wrong}"
suggestion: "{how to fix}"
auto_fixable: true|false
owasp_ref: "A03:2021"
summary:
total_findings: {N}
critical: {N}
high: {N}
medium: {N}
low: {N}
Severity guide (security-specific)
- critical: exploitable remotely without auth, data breach risk
- high: exploitable with low complexity, significant impact
- medium: requires specific conditions, moderate impact
- low: defense-in-depth improvement, not directly exploitable
- info: hardening suggestion
Veto power
Security findings of severity critical or high trigger automatic verdict "fail" regardless of other judges. A security veto cannot be overridden by scoring — it must be fixed.
Reporting Policy (SE-066)
Coverage-first review under Opus 4.7. Ver docs/rules/domain/review-agents-reporting-policy.md. Cada finding con {confidence, severity}; filter downstream rankea.
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.
- 6d ago First seen · 78 lines · 20 tokens per session scan A c17236ee60bc
security-judge is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 641 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 2026-09-06.
Other agents, from other repositories
architect
Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.
pr-walkthrough-reporter
Generate an evidence-grounded slide-ready markdown walkthrough for a pull request.
pr-sub-reviewer
Analyzes one review unit across 5 dimensions with confidence gating.
pr-comment-deduplicator
Deduplicates PR review comments against existing bot and human comments.
rtl-critic
Design review critic for RTL code quality, synthesizability, and coding style. Saves review reports to reviews/.md. (Opus). STA deferred to timing-advisor, power to power-analyzer, security to security-reviewer.
uvm-reviewer
UVM testbench quality reviewer. Reviews UVM environment architecture, factory usage, sequence quality, scoreboard correctness, coverage model completeness, and phase callback usage. Produces review reports in reviews/.