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/agent-interoperabilitygit 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 | $0.01162 |
| Opus 5 | $0.00000 | $0.00581 |
| Sonnet 5 | $0.00000 | $0.00232 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade B, and why
agent-interoperability scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Codex discovers project skills from `.agents/skills/` and reads the project MCP configuration from [.codex/config.toml](../../.codex/config.toml). The checked-in server configuration deliberately allow-lists read-only to How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Interoperability
Codomyrmex keeps the reasoning and safety workflows portable while leaving transport and permission settings to each runtime.
Shared skills
The canonical repository-scoped skills live under .agents/skills/:
| Skill | Use it for |
|---|---|
first-principles |
Reduce a problem to verified facts, constraints, and decisions |
red-team |
Exercise realistic abuse, failure, and permission paths |
systems-thinking |
Trace dependencies, feedback loops, delays, and second-order effects |
mcp-tool-use |
Inspect, constrain, approve, execute, and verify tool calls |
agent-interop |
Transfer work between Codex, Claude Code, and Hermes |
They follow the portable Agent Skills specification: concise frontmatter, progressive disclosure, and supporting resources only when needed. A runtime-specific adapter should point to these files rather than fork their logic.
Runtime setup
Codex
Codex discovers project skills from .agents/skills/ and reads the project MCP configuration from .codex/config.toml. The checked-in server configuration deliberately allow-lists read-only tools and keeps approval mode at prompt.
Inspect the server from the repository root:
uv run python scripts/model_context_protocol/run_mcp_server.py --profile readonly --list-tools
codex mcp list
The server also supports a full profile for explicitly authorized local work, but the checked-in Codex and Claude examples use readonly. The Codex MCP documentation describes stdio and Streamable HTTP servers, tool filtering, timeouts, and approval modes. Project configuration is used only when the project is trusted by Codex.
Claude Code
Claude Code discovers skills from .claude/skills/ and project MCP servers from .mcp.json. The additive wrappers under .claude/skills/ point to the canonical files without duplicating them. Use config/claude_code_mcp.example.json as an explicit project opt-in, and read the matching portable skill under .agents/skills/ when a Claude-specific wrapper is not present.
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 · 78 lines · 0 tokens per session scan B c8f627e5471a
agent-interoperability 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 1,162 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.