agent-interoperability

A set of shared coding-agent workflows that can work across Codex, Claude Code, and Hermes. It covers fact-checking, security testing, systems analysis, tool use, and transferring work between agents.

In plain words
What is it for?
Use it to break down problems, test failure or abuse paths, trace system dependencies, control tool calls, and hand work between agents.
Why use it?
It keeps reasoning and safety practices consistent when work moves between different agent programs.

Agent

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.

agentmods
npx agentmods add agents/docxology/codomyrmex/agent-interoperability
Clone the repo
git clone --depth 1 https://github.com/docxology/codomyrmex
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00000 $0.01162
Opus 5 $0.00000 $0.00581
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured 2d ago against content hash c8f627e5471a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
docs/agents/agent-interoperability.md · 78 lines

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.

Read the full file on GitHub · 78 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.

  1. 2d ago First seen · 78 lines · 0 tokens per session scan B c8f627e5471a

Subscribe to this mod's changes

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.