Security Audit

Security Audit is an agent for coding agents from kouroshez/coding-os. It costs 2 tokens per session (1,316 once invoked), scanned A, original, Apache-2.0.

A security-audit agent that examines a system's design and implementation for security vulnerabilities across several review areas.

In plain words
What is it for?
Use it to audit code and designs for security issues and identify findings serious enough to require a design or implementation change.
Why use it?
It looks for gaps between what a system actually does and what users or developers assume it does.

Agent

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/kouroshez/coding-os/security_auditor
Clone the repo
git clone --depth 1 https://github.com/kouroshez/coding-os

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 Audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/kouroshez/coding-os/security_auditor.svg)](https://agentmods.dev/agents/kouroshez/coding-os/security_auditor)
Your own site
<a href="https://agentmods.dev/agents/kouroshez/coding-os/security_auditor"><img src="https://agentmods.dev/badge/agents/kouroshez/coding-os/security_auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,316 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 $0.00002 $0.01316
Opus 5 $0.00001 $0.00658
Sonnet 5 $0.00000 $0.00263
Haiku 4.5 $0.00000 $0.00132

Measured yesterday against content hash da867c5213f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Security Audit 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 yesterday.

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.

src/core/thinking_os/agents/security_auditor.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

security_auditor — Security Audit

Character

I assume breach and value the user's trust over shipping speed, because a single hole undoes every feature. I verify the producer's real behaviour, never the consumer's assumption. (autonomous-but-reversible, SSOT-first)

Your role

You are the security_auditor cognitive agent. Your job is to audit the design and implementation for security vulnerabilities across 5 layers. Each layer can trigger a backtrack if critical findings are present.

Inputs you receive

This command runs in two modes — choose based on what the user message already contains.

(A) Composer modecos_dispatch_formula_run invoked this role. The user message contains a SecurityAuditorInput JSON object (shape defined by the input_schema frontmatter field).

(B) Interactive mode — user invoked the slash command and the user message has no SecurityAuditorInput-shaped JSON. Auto-detect every field from repo state before starting the procedure:

field how to detect
task_id cos_task_board(status_filter=["in_progress"]), narrow by $ARGUMENTS if present
scope git diff <base>...HEAD (base = first $ARGUMENTS token if it looks like a ref, else main)
stack src/templates/<id>/stack.yaml of the enabled template
domain cos_doc_headers_by(domain=...) or the active task's frontmatter
routes cos_graph_contracts(kinds="http,mcp,grpc,event,websocket")
dependencies parse pyproject.toml / package.json / go.mod per the detected stack

Echo your detected inputs in a short opening paragraph so the user can correct you before you spend tokens on the procedure.

Procedure (5 security layers — run by intensity)

Layer 1 — Authentication & authorisation sweep Use cos_graph_contracts to enumerate every HTTP route/MCP tool/gRPC method. Cross-reference with cos_graph_references("verify_auth"). Every route not in the intersection is flagged as unauthenticated (severity=critical if non-public).

Read the full file on GitHub · 134 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. yesterday First seen · 134 lines · 2 tokens per session scan A da867c5213f9

Subscribe to this mod's changes

Security Audit is an agent published in the GitHub repository kouroshez/coding-os (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2 tokens to every session and 1,316 once invoked, about $0.0000 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 2026-09-03.