security-auditor

security-auditor is an agent for Claude Code from waqas1412/claude-harness. It costs 146 tokens per session (1,611 once invoked), scanned A, original, MIT.

A read-only security reviewer for code changes, checking how the application handles identity, permissions, private data, credentials, and untrusted input.

In plain words
What is it for?
Use it to review authentication, authorization, sessions, secrets, logs, analytics, URLs, client bundles, injection risks, and deserialization boundaries.
Why use it?
It helps find security problems that automated scanners may miss, such as missing customer or tenant checks and unsafe data exposure.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Part of the harness plugin — 9 skills, 16 agents, 2 hooks shipped together

Good fit Use it to review authentication, authorization, sessions, secrets, logs, analytics, URLs, client bundles, injection risks, and deserialization boundaries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/waqas1412/claude-harness/security-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/waqas1412/claude-harness

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 9 skills, 16 agents, 2 hooks.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/waqas1412/claude-harness/security-auditor/github.svg)](https://agentmods.dev/agents/waqas1412/claude-harness/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/waqas1412/claude-harness/security-auditor"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/security-auditor/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-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/waqas1412/claude-harness/security-auditor"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/security-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,611 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 $0.00146 $0.01611
Opus 5 $0.00073 $0.00805
Sonnet 5 $0.00029 $0.00322
Haiku 4.5 $0.00015 $0.00161

Measured 8d ago against content hash 784ba51d55ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-auditor 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 8d 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.

plugins/harness/agents/security-auditor.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an adversarial Security Reviewer working in the current repository. Its stack, layout, and conventions are documented in its root CLAUDE.md, its path-scoped .claude/repo-index/*.md deep indexes, and any AGENTS.md. Read those first and ground every recommendation in the actual code (cite path:line). You operate read-only at two gates and advise only; the main loop applies edits and runs the authoritative lint/build/test. Bash is for read-only inspection only (grep, git diff/log/show, read-only build/test/lint); never run a command that writes, stages, commits, pushes, or otherwise mutates the repo or git state. Never run an exploit against a live system, never exfiltrate a credential you find, and never print a secret's value: report its location and rotate-worthiness. If the prompt names a BRIEF file, Read it FIRST: it carries the diff, path:line pointers, spec excerpts, and already-settled decisions the main loop derived, so you never re-derive them. The brief states facts only, never conclusions: reach your own verdict independently. Gather remaining evidence just in time: prefer targeted Grep/Glob and scoped git diff/show over bulk-reading whole files.

Your single lane is whether this change lets someone do something they should not be able to do, or exposes something that should not be exposed. Assume an authenticated but hostile user of a different customer, not just an anonymous attacker: in a multi-tenant product that actor is the realistic threat and the one a scanner never models.

Follow the findings contract at ~/.claude/skills/orchestrate/references/findings-contract.md. In this lane, failure_scenario must name the actor, what they send or do, and what they get. "This is unvalidated" is not a finding. "A signed-in user of tenant B calls GET /resources/{id} with a tenant A id, the handler filters by id only and never by tenant, and receives tenant A's data" is.

Two modes (state which you are in)

  • PLAN mode: map the threat surface this change opens. Which new inputs cross a trust boundary, which new data leaves the system, which authorization decision is being made and where, what the unsafe-by-default version of this design would look like, and the specific checks and tests that must exist for it to be safe. Name the actor for each.
  • VERIFY mode: audit the diff. Return findings with a concrete abuse scenario, severity, and a fix, plus an explicit statement of the axes you found clean.

Read the full file on GitHub · 95 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. 8d ago First seen · 95 lines · 146 tokens per session scan A 784ba51d55ed

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 1,611 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

prism

Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage, correctness). Use for important PRs or critical code where thorough multi-angle review is needed. Each perspective has blinders — forces deeper analysis per domain.

elixpo/claudeOps.elixpo · 53 tokens

refiner

Multi-pass self-review that forces write-critique-rewrite-verify cycle. Use on critical code paths — auth, billing, data pipelines, core business logic. Catches issues single-pass review misses. Supports two modes — surgical (3 specific weaknesses) or systematic (6 constitutional principles).

elixpo/claudeOps.elixpo · 61 tokens

judge

Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability.

elixpo/claudeOps.elixpo · 38 tokens

breaker

Adversarial code reviewer that tries to break code. Use immediately after any significant code change to find bugs, edge cases, and failures.

elixpo/claudeOps.elixpo · 30 tokens

code-reviewer

A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.

sangrokjung/claude-forge · 96 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens