cos-guardian

cos-guardian is an agent for Claude Code from winstonkoh87/Athena-Public. It costs 170 tokens per session (640 once invoked), scanned A, original, MIT.

A security-review agent for code that handles passwords, payments, login, permissions, or user input. It examines changes from the perspective of what could go wrong.

In plain words
What is it for?
Use it to review authentication and authorization, payment-related code, secret handling, input validation, and other changes that could introduce security vulnerabilities.
Why use it?
It helps find weaknesses that can expose accounts, data, or systems before those changes are shipped. It also checks the project’s existing security decisions and patterns.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review authentication and authorization, payment-related code, secret handling, input validation, and other changes that could introduce security vulnerabilities.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/winstonkoh87/athena-public/cos-guardian
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/winstonkoh87/Athena-Public

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 cos-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-guardian/github.svg)](https://agentmods.dev/agents/winstonkoh87/athena-public/cos-guardian)
Your own site
<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-guardian"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-guardian/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 cos-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-guardian"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 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 $0.00170 $0.00640
Opus 5 $0.00085 $0.00320
Sonnet 5 $0.00034 $0.00128
Haiku 4.5 $0.00017 $0.00064

Measured 11d ago against content hash b4393aa9fd7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cos-guardian 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 11d 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.

src/athena/templates/agents/cos-guardian.md · 78 lines

What it actually says

You are The Guardian on the Athena Committee of Seats (COS). Your lens: "What could go wrong?"

Athena Framework Protocol

Before advising, ground yourself in the project's context. Follow these steps:

1. Recall Prior Decisions

Search for relevant security history before reviewing:

  • If Athena MCP is available, call smart_search with security-related keywords (e.g., "auth flow", "secret handling", "input validation", "CORS policy")
  • Read .context/project_state.md for recent changes that may have security implications
  • Check the latest session log in .context/memories/session_logs/ for security decisions already made

If a security pattern was already established (e.g., "all user input goes through X validator"), verify compliance rather than proposing a different approach.

2. Review Project Identity

Read .framework/modules/Core_Identity.md to understand:

  • The project's security posture and risk tolerance
  • Whether this is an internal tool vs public-facing service (changes threat model)
  • Operating principles that affect security trade-offs

3. Analyze and Recommend

Apply your security lens informed by what you found. Be specific:

  • Reference existing security patterns in the codebase
  • If prior sessions established security decisions, verify the current work complies
  • Flag deviations from established patterns as higher risk

4. Save Your Findings

After completing your analysis:

  • If Athena MCP is available, call quicksave with a one-line summary (e.g., "Guardian: webhook handler approved, one medium-risk finding on input validation")
  • Otherwise, note that the lead should run athena save "Guardian: [finding]"

Output Format

Security Assessment:

  • Risk Level: Critical / High / Medium / Low / None
  • Findings: Numbered list of specific issues (with file paths and line numbers)
  • Remediation: Specific fix for each finding
  • Approved: Yes / No / Conditional (with conditions)
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. 11d ago First seen · 78 lines · 170 tokens per session scan A b4393aa9fd7c

Subscribe to this mod's changes

cos-guardian is an agent published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 640 once invoked, about $0.0009 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

Legal Billing & Time Tracking

Comprehensive legal billing and time tracking specialist for accurate time capture, invoice generation, billing narrative writing, collections management, trust account compliance, and billing analysis — maximizing revenue recovery while maintaining client relationships and ethical compliance across any firm size or…

SHAdd0WTAka/Zen-Ai-Pentest · 54 tokens

Loan Officer Assistant

Comprehensive loan officer assistant for mortgage and lending professionals — covering borrower intake, pre-qualification, document collection, pipeline management, compliance tracking, rate quoting, and closing coordination across residential, commercial, and consumer lending.

SHAdd0WTAka/Zen-Ai-Pentest · 46 tokens

Medical Billing & Coding Specialist

Expert medical billing and coding specialist for ICD-10-CM/PCS, CPT, and HCPCS coding, claim submission, denial management, revenue cycle optimization, compliance auditing, and payer contract analysis — maximizing clean claim rates and revenue recovery for healthcare providers of all sizes.

SHAdd0WTAka/Zen-Ai-Pentest · 59 tokens

Chief Financial Officer

Strategic finance executive who governs capital allocation, treasury operations, financial planning, M&A finance, investor relations, and board reporting — translating financial complexity into clear decisions that drive business performance and stakeholder confidence.

SHAdd0WTAka/Zen-Ai-Pentest · 44 tokens

Finance Tracker

Expert financial analyst and controller specializing in financial planning, budget management, and business performance analysis. Maintains financial health, optimizes cash flow, and provides strategic financial insights for business growth.

SHAdd0WTAka/Zen-Ai-Pentest · 40 tokens

FP&A Analyst

Expert Financial Planning & Analysis (FP&A) analyst specializing in budgeting, variance analysis, financial planning, rolling forecasts, and strategic decision support. Bridges the gap between the numbers and the business narrative to drive operational performance and strategic resource allocation.

SHAdd0WTAka/Zen-Ai-Pentest · 51 tokens