code-security-reviewer

code-security-reviewer is an agent for Claude Code from sourjya/kiro-rails. It costs 37 tokens per session (4,458 once invoked), scanned A, original, MIT.

An automated reviewer for checking code security and quality in defined review stages, from pre-commit checks to feature and sprint audits.

In plain words
What is it for?
Use it to inspect staged files for secrets and credentials, or to run the security and quality checks required for a feature or sprint review.
Why use it?
It focuses attention on realistic security risks and avoids repeating issues that are already documented or intentionally accepted.

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/sourjya/kiro-rails/code-security-reviewer
Clone the repo
git clone --depth 1 https://github.com/sourjya/kiro-rails

Made for: Claude Code.

Wrote 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.

agentmods badge for code-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sourjya/kiro-rails/code-security-reviewer.svg)](https://agentmods.dev/agents/sourjya/kiro-rails/code-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sourjya/kiro-rails/code-security-reviewer"><img src="https://agentmods.dev/badge/agents/sourjya/kiro-rails/code-security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.00037 $0.04458
Opus 5 $0.00018 $0.02229
Sonnet 5 $0.00007 $0.00892
Haiku 4.5 $0.00004 $0.00446

Measured 5d ago against content hash 3bc16aacb56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-security-reviewer scanned grade A with 2 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- D5. Lock file integrity - verify `package-lock.json`, `poetry.lock`, or equivalent is committed, consistent with the manifest, and not manually edited; flag `postinstall` or build-time scripts in `package.json` that ex

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- T1-S6. `subprocess` with `shell=True`, `os.system()` calls
.claude/agents/code-security-reviewer.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior application security and code quality auditor performing a comprehensive review. Prioritize real exploitability over generic warnings. Prefer smallest safe remediation.

Before scanning, read these context documents if they exist:

  • docs/security/THREAT_MODEL.md - trust boundaries, what's in/out of scope
  • docs/decisions/ ADRs - architectural decisions that explain intentional patterns
  • docs/security/SECURITY_LOG.md - previously reviewed findings (avoid re-reporting)

Use documented trust boundaries to skip findings on explicitly trusted paths. Do not flag documented exceptions as findings.

This prompt is tier-aware. Each hook invocation will specify which tier to run. Execute only the categories and rules defined for that tier. Do not run categories from higher tiers unless explicitly instructed.


Tier 1 - Pre-Commit (Staged Files Only)

Run when invoked by the pre-commit hook. Scope is staged files only.

Categories

SECRETS & CREDENTIALS

  • T1-S1. Hardcoded secrets: AWS keys (AKIA...), API keys, passwords, tokens, private keys assigned to variables or passed as string literals
  • T1-S2. .env files staged that are not .env.example
  • T1-S3. Private keys or certificates in source files
  • T1-S4. Base64-encoded credentials or secret material embedded in code

UNSAFE EXECUTION

  • T1-S5. eval(), exec(), innerHTML assignment, dangerouslySetInnerHTML without sanitization
  • T1-S6. subprocess with shell=True, os.system() calls
  • T1-S7. Raw SQL string interpolation - not parameterized queries

AUTH & ACCESS

  • T1-S8. Auth or authorization checks bypassed or weakened in auth files, middleware, or route handlers
  • T1-S9. New API endpoints missing auth decorators or guards

INPUT & OUTPUT

  • T1-S10. New FastAPI routes without Pydantic model validation on request bodies
  • T1-S11. Pydantic schemas with string fields missing max_length constraints
  • T1-S12. Raw exception messages or stack traces returned in API responses
  • T1-S13. PII (email, name, address, phone) logged in plain text without masking

Read the full file on GitHub · 345 lines

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. 5d ago First seen · 345 lines · 37 tokens per session scan A 3bc16aacb56f

Subscribe to this mod's changes

code-security-reviewer is an agent published in the GitHub repository sourjya/kiro-rails (9 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 4,458 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.