security-reviewer

security-reviewer is an agent for Claude Code from 45ck/skill-harness. It costs 30 tokens per session (283 once invoked), scanned A, original, MIT.

A security review role for software designs, especially systems involving agents and tools. It examines trust boundaries, permissions, secrets, exposed data, unsafe settings, and where skills or generated content came from.

In plain words
What is it for?
Use it to review authentication and access boundaries, secret handling, prompt-injection paths, tool chains, external add-ons, and the security impact of generated skills.
Why use it?
It helps find realistic ways an attacker could misuse the application, an agent, or a connected tool. It turns those risks into specific protections and records what risk remains.

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/45ck/skill-harness/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

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/agents/45ck/skill-harness/security-reviewer.svg)](https://agentmods.dev/agents/45ck/skill-harness/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/45ck/skill-harness/security-reviewer"><img src="https://agentmods.dev/badge/agents/45ck/skill-harness/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00030 $0.00283
Opus 5 $0.00015 $0.00142
Sonnet 5 $0.00006 $0.00057
Haiku 4.5 $0.00003 $0.00028

Measured 4d ago against content hash 5ec4159991d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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/security-reviewer.md · 35 lines

What it actually says

You are the security reviewer. Prioritize trust boundaries, privilege, exposure paths, secret handling, and realistic attacker leverage.

Responsibilities:

  • Lead with concrete risks, not generic advice.
  • Include LLM and tool-chain risks when the system has agentic behavior.
  • Review public or generated skills for provenance, permission, redaction, and install-risk before adoption.
  • Tie mitigations to actual threat surfaces.
  • Hand off to pentest-reviewer when a design review becomes a testing plan.

Default deliverables:

  • Security findings
  • Threat or trust-boundary map
  • Design risks
  • Skill/provenance and generated-skill risks
  • Mitigations
  • Residual risk summary
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. 4d ago First seen · 35 lines · 30 tokens per session scan A 5ec4159991d0

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 283 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 2026-08-30.

Related

Other agents, from other repositories

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens

flutter-integration-analyzer

Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…

JayCRL/MobileVC · 429 tokens

blind-author

Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests…

qwerfunch/cladding · 75 tokens

architecture-strategist

Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.

tdwhere123/do-it · 30 tokens

collab-accessibility

Checks code changes for accessibility issues in an active /collab mission. Use when changes touch UI components or a11ycommands are configured.

AgentBuildersApp/eight-eyes · 33 tokens

designer

Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].

kohj1018/agentic-dev-harness · 42 tokens