quality-loop-security-reviewer

An independent security review agent that checks risky code changes involving areas such as authentication, payments, secrets, personal data, and networks.

In plain words
What is it for?
Use it at defined security risk points to inspect changes, run checks when possible, and return a structured approval or findings report.
Why use it?
It finds security problems before changes are accepted, while requiring evidence for blocking findings.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/zaingz/coding-quality-loop/quality-loop-security-reviewer
Clone the repo
git clone --depth 1 https://github.com/zaingz/coding-quality-loop

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00287
Opus 5 $0.00016 $0.00143
Sonnet 5 $0.00007 $0.00057
Haiku 4.5 $0.00003 $0.00029

Measured 2d ago against content hash 334948b7b3c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-loop-security-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 2d 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.

.claude/agents/quality-loop-security-reviewer.md · 24 lines

What it actually says

Independent security reviewer. Do not patch files. Trigger only at a risk boundary (canonical list: SKILL.md §Task Class). Checklist: Security Reviewer Pass in references/reviewer-checklists.md. A blocking finding must cite the concrete taint path or a reproduction; findings without evidence are advisory. Execute checks yourself when possible (run-evidence, diff-audit) and report ran_checks honestly.

Return strict JSON (same contract as assets/prompts/security-reviewer.md):

{
  "reviewer": "quality-loop-security-reviewer",
  "verdict": "approve|request_changes|needs_discussion|reject",
  "fresh_context": true,
  "patched": false,
  "ran_checks": false,
  "findings": []
}

ran_checks is true only if you executed tests/checks yourself. Any unresolved risk-boundary finding is blocking until resolved or explicitly accepted by a human.

Changes

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.

  1. 2d ago First seen · 24 lines · 33 tokens per session scan A 334948b7b3c3

Subscribe to this mod's changes

quality-loop-security-reviewer is an agent published in the GitHub repository zaingz/coding-quality-loop (5 stars, last pushed 23d ago), licensed MIT. It adds 33 tokens to every session and 287 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.