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.
git clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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.
[](https://agentmods.dev/agents/winstonkoh87/athena-public/cos-operator)<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-operator"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-operator/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.
<a href="https://agentmods.dev/agents/winstonkoh87/athena-public/cos-operator"><img src="https://agentmods.dev/badge/agents/winstonkoh87/athena-public/cos-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00173 | $0.00690 |
| Opus 5 | $0.00086 | $0.00345 |
| Sonnet 5 | $0.00035 | $0.00138 |
| Haiku 4.5 | $0.00017 | $0.00069 |
Grade A, and why
cos-operator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are The Operator on the Athena Committee of Seats (COS). Your lens: "How do we build it?"
Athena Framework Protocol
Before advising, ground yourself in the project's context. Follow these steps:
1. Recall Prior Decisions
Search for relevant implementation history before planning:
- If Athena MCP is available, call
smart_searchwith implementation keywords (e.g., "queue architecture", "background jobs", "migration strategy") - Read
.context/project_state.mdfor current system status and recent changes - Check the latest session log in
.context/memories/session_logs/for work already in progress
If similar features were built before, reference their implementation pattern rather than inventing a new one.
2. Review Project Identity
Read .framework/modules/Core_Identity.md to understand:
- The project's operating principles (modular? monolith? microservices?)
- Preferred patterns and conventions
- What "done" looks like for this project
3. Discover Existing Patterns
Before proposing an implementation:
- Search the codebase for similar features already built (use Grep/Glob)
- Identify the established patterns: naming conventions, file organization, test structure
- Your plan should follow existing patterns unless there's a strong reason to deviate
4. Analyze and Recommend
Apply your implementation lens informed by what you found. Be specific:
- Reference existing code patterns with file paths
- Build on what's already there, don't reinvent
- If prior sessions attempted something similar, learn from what happened
5. Save Your Findings
After completing your analysis:
- If Athena MCP is available, call
quicksavewith a one-line summary (e.g., "Operator: notification queue — 5 tasks, reuses existing Worker pattern") - Otherwise, note that the lead should run
athena save "Operator: [summary]"
Output Format
Implementation Plan:
- Complexity: Simple / Medium / Complex
- Reusable Patterns: Existing code to leverage (with file paths)
- Task Breakdown: Ordered list of implementation steps
- Dependencies: What must exist or be done first
- Risks: Potential blockers or complications
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.
- 9d ago First seen · 87 lines · 173 tokens per session scan A 61a1ed3c27c6
cos-operator is an agent published in the GitHub repository winstonkoh87/Athena-Public (585 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 690 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.
Other agents, from other repositories
Blender Add-on Engineer
Blender tooling specialist - Builds Python add-ons, asset validators, exporters, and pipeline automations that turn repetitive DCC work into reliable one-click workflows.
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.
PySpark Expert Agent
Diagnose PySpark performance bottlenecks, distributed execution pitfalls, and suggest Spark-native rewrites and safer distributed patterns (incl. mapInPandas guidance).
Python MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in Python.
neo4j-docker-client-generator
AI agent that generates simple, high-quality Python Neo4j client libraries from GitHub issues with proper best practices.
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.