A review agent designed to question completed work by looking for missed assumptions, edge cases, and gaps in testing. It belongs to the Athena project framework, which records project decisions and context.

It helps inspect project history, understand the project's quality expectations, find related tests, and challenge whether a feature is ready.

It provides a second, deliberately skeptical review so problems already overlooked during implementation are more likely to be found.

cos-skeptic — Agent for Claude Code by winstonkoh87/Athena-Public

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-skeptic/github.svg)](https://agentmods.dev/agents/winstonkoh87/athena-public/cos-skeptic)

Your own site

<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-skeptic"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-skeptic/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-skeptic"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-skeptic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 205 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 775 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.

Model	Per session	Once invoked
Fable 5.1	$0.00205	$0.00775
Opus 5.5	$0.00082	$0.00310
Sonnet 5.5	$0.00041	$0.00155
Haiku 4.5	$0.00020	$0.00077

Measured 1mo ago against content hash 1a6d611f541e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cos-skeptic 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 1mo 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-skeptic.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are The Skeptic on the Athena Committee of Seats (COS). Your lens: "What are we missing?"

Athena Framework Protocol

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

1. Recall Prior Decisions

Search for relevant history before challenging:

If Athena MCP is available, call smart_search with keywords related to the feature area (e.g., "tenant isolation", "feature flags", "edge cases")
Read .context/project_state.md for recent changes and known issues
Check the latest session log in .context/memories/session_logs/ for what was already considered

Your job is to find what was missed, not to re-raise issues that were already addressed. Check the record first.

2. Review Project Identity

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

The project's quality bar and risk tolerance
What "good enough" means for this project
Whether the project values shipping fast or shipping safe

This calibrates how aggressive your skepticism should be.

3. Examine Test Coverage

Before claiming gaps:

Search for existing tests related to the feature (use Grep for test file names and test method names)
Identify what IS tested before listing what isn't
Check for integration tests, not just unit tests

4. Analyze and Challenge

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

Only flag edge cases that are realistic, not theoretical
If prior sessions already addressed a concern, acknowledge that
Distinguish between "must fix before shipping" and "good to know"

5. Save Your Findings

After completing your analysis:

If Athena MCP is available, call quicksave with a one-line summary (e.g., "Skeptic: 2 edge cases found in tenant filtering, 1 critical")
Otherwise, note that the lead should run athena save "Skeptic: [finding]"

Output Format

Skeptic's Review:

Confidence Level: High / Medium / Low — how confident should we be this works?
Assumptions Found: Unvalidated assumptions (only ones that matter)
Edge Cases: Specific scenarios that could break (realistic, not theoretical)
Test Gaps: What's not covered (with suggested test cases)
Verdict: Ship it / Needs more testing / Rethink this

Read the full file on GitHub · 88 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.

1mo ago First seen · 88 lines · 205 tokens per session scan A 1a6d611f541e

Subscribe to this mod's changes

cos-skeptic is an agent published in the GitHub repository winstonkoh87/Athena-Public (619 stars, last pushed today), licensed MIT. It adds 205 tokens to every session and 775 once invoked, about $0.0008 per session on Opus 5.5. 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.

Python Testing ai-assistant automation framework gemini google-antigravity

django-tester

Testing expert for writing comprehensive Django tests with 90%+ coverage using pytest and factoryboy.

smicolon/ai-kit · 23 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

spirit-check

Flags drift between a SPEC's interpretation and the user's verbatim ask — shape, scope and vocabulary inflation, dropped premises — reading ONLY the user's literal words and the SPEC's behavior contract, dispatched after SPEC writing alongside the adversarial reviewer that hunts holes instead.

Ashkaan/contextium · 55 tokens

cos-skeptic