lenserfight: Skill for Claude Code

.agents/skills/security-reviewer/SKILL.md

security-reviewer is a skill for Claude Code from conectlens/lenserfight. It costs 50 tokens per session (434 once invoked), scanned A, original, MIT.

A security review guide for LenserFight applications and selected code areas. It covers login, permissions, data exposure, input checks, database row-level security, and related application flows.

In plain words
What is it for?
Use it to review modules, files, migrations, authentication flows, APIs, logs, or interactions between the React client, command-line tool, Supabase, and edge functions.
Why use it?
It helps identify how attackers might access data, bypass permissions, abuse requests, or exploit unsafe failures within the chosen scope.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is conectlens/lenserfight's own configuration. It tells Claude Code how to work on lenserfight itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lenserfight configures →

Reuse

Borrowing it

Nothing to install: this file belongs to conectlens/lenserfight. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/conectlens/lenserfight/main/.agents/skills/security-reviewer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/conectlens/lenserfight

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/conectlens/lenserfight/security-reviewer/github.svg)](https://agentmods.dev/skills/conectlens/lenserfight/security-reviewer)
Your own site
<a href="https://agentmods.dev/skills/conectlens/lenserfight/security-reviewer"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/security-reviewer/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.

agentmods 80×15 button for security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/conectlens/lenserfight/security-reviewer"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.00434
Opus 5 $0.00025 $0.00217
Sonnet 5 $0.00010 $0.00087
Haiku 4.5 $0.00005 $0.00043

Measured 9d ago against content hash 4aaa7d365343, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

.agents/skills/security-reviewer/SKILL.md · 50 lines

What it actually says

Run a security review for $ARGUMENTS.

Purpose Review security of the requested scope only. Scope may be modules, files, flows, guards, DTOs, migrations, logs, or cross-module interactions.

Approach

  • Let the requested scope drive the review depth.
  • Prefer architectural reasoning over checklist dumping.
  • Review only the code and docs needed for the given scope.
  • Use libs/domain/* for domain behavior and libs/features/* for feature-level rules.

Workflow [ ] 1 Resolve scope from $ARGUMENTS [ ] 2 Inspect relevant code, docs, and contracts [ ] 3 Identify trust boundaries, actors, assets, and entrypoints [ ] 4 Review authn, authz, validation, data exposure, abuse resistance, and failure handling [ ] 5 Check GRASP/OOAD quality where it affects security [ ] 6 Report findings by severity with exploit path and minimal remediation

Core review areas

  • authentication
  • authorization
  • tenant/workspace isolation
  • DTO and input validation
  • sensitive data exposure
  • idempotency and replay resistance
  • rate limiting and abuse controls
  • transactional integrity and race conditions
  • provider/webhook trust
  • logging and error sanitization

Design rules

  • Prefer low coupling and high cohesion.
  • Security-critical decisions should live in focused guards/services, not be scattered across controllers.
  • Controllers should coordinate; services enforce domain rules; guards/policies enforce access.
  • Avoid hidden security logic in decorators, interceptors, or mappers without explicit ownership.
  • Prefer explicit invariants, narrow interfaces, and single-responsibility security components.

Load references only when needed

Review process and severity model
See the reference guide

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 50 lines · 50 tokens per session scan A 4aaa7d365343

Subscribe to this mod's changes

security-reviewer is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed 29d ago), licensed MIT. It adds 50 tokens to every session and 434 once invoked, about $0.0003 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.