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.
npx agentmods add agents/docxology/codomyrmex/technical_overviewgit clone --depth 1 https://github.com/docxology/codomyrmexWhat 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 | $0.00000 | $0.03585 |
| Opus 5 | $0.00000 | $0.01792 |
| Sonnet 5 | $0.00000 | $0.00717 |
| Haiku 4.5 | $0.00000 | $0.00359 |
Grade A, and why
technical_overview 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 2d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Code Editing Submodule - Technical Overview
This document provides a detailed technical overview of the AI Code Editing submodule (agents/ai_code_editing/).
1. Introduction and Purpose
The AI Code Editing module is a pivotal component of the Codomyrmex project, engineered to provide sophisticated AI-driven assistance for source code manipulation and understanding. It directly addresses the need for intelligent automation in common development workflows, including code generation, refactoring, summarization, and bug detection. By interfacing with advanced Large Language Models (LLMs), this module aims to significantly boost developer productivity, improve code quality, and streamline complex coding tasks within the Codomyrmex ecosystem. Its core responsibility is to act as the primary interface between the developer (or other automated systems) and AI models for all code-related intelligence.
2. Architecture
The module's architecture is designed around a set of interacting components that handle the lifecycle of an AI-assisted code editing task, from receiving a request to delivering a result.
- Key Components/Sub-modules:
LlmConnectorService: Abstracting the communication layer with various LLM providers (e.g., OpenAI, Anthropic). This component manages API endpoint interactions, request/response (de)serialization, and API key handling (retrieved from secure configurations).PromptOrchestrator: Responsible for dynamically constructing tailored prompts for specific tasks (e.g., generating a Python function, refactoring a Java class, summarizing a code block). It utilizes prompt templates and injects relevant context (code snippets, user instructions, style guides) to optimize LLM outputs.CodeParserUtil: (Optional, but highly recommended for advanced features) Integrates with code parsing libraries (e.g., tree-sitter, ANTLR, or project-specific parsers likecased/kitif available) to transform source code into Abstract Syntax Trees (ASTs) or other structured formats. This allows for more precise context extraction, targeted modifications, and validation of LLM outputs.ContextAggregator: Gathers and prepares the necessary context for the LLM. This can include the current code block, related functions or classes, imported modules, project-wide coding conventions, or relevant documentation snippets. Effective context aggregation is crucial for the quality of LLM-generated code.ChangeApplicator: Takes the raw code suggestions from the LLM and intelligently applies them to the target source file(s). This may involve merging changes, ensuring proper formatting according to project standards, and potentially running linters or pre-commit hooks on the modified code.McpToolImplementations: Provides the concrete logic for tools exposed via the Model Context Protocol (MCP), such asgenerate_code_snippetandrefactor_code_snippet. These implementations orchestrate the services of the other components to fulfill MCP requests.
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.
- 2d ago First seen · 180 lines · 0 tokens per session scan A 26aa94475647
technical_overview is an agent published in the GitHub repository docxology/codomyrmex (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,585 tokens. 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
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.