clodbridge AGENTS.md

Project instructions and technical reference for clodbridge, including its MCP tools, agent spawning, architecture, and development workflow. MCP is a standard way for AI assistants to discover and use external tools; the document also describes agents for validating MCP servers and explaining the codebase.

In plain words
What is it for?
Use it when working on clodbridge, validating an MCP server, debugging tool discovery or responses, or understanding the project's architecture and delivery process.
Why use it?
It gives developers and coding agents project-specific guidance in one place. It clarifies which specialised agents are available and when they should be used.

Instructions file for CodexOpenCode

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 instructions/rethunk-ai/clodbridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/Rethunk-AI/clodbridge

Made for: Codex, OpenCode.

Per session 1,838 This file is loaded in full into every session.
When invoked 1,838 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01838 $0.01838
Opus 5 $0.00919 $0.00919
Sonnet 5 $0.00368 $0.00368
Haiku 4.5 $0.00184 $0.00184

Measured 2d ago against content hash b0e849c186fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clodbridge AGENTS.md 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.

AGENTS.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

clodbridge -- Technical Reference

This document is the primary reference for AI agents and developers working with clodbridge. It covers the MCP tools API, agent spawning mechanics, architecture, and development workflow.

For user-facing guidance (creating rules, skills, agents), see HUMANS.md.

Available Agents

clodbridge exposes three specialized subagents that Claude Code can spawn proactively:

1. mcp-validator (Claude Opus 4.6)

Specialization: Validates MCP server implementations and debugs integration issues.

Use when:

  • Testing a newly created MCP tool before deployment
  • Debugging why Claude Code can't discover an MCP server
  • Validating that tool responses conform to the MCP schema
  • Checking that glob patterns correctly match files
  • Profiling MCP server performance

What it does:

  • Calls MCP tools and validates responses
  • Verifies data conforms to MCP specifications
  • Diagnoses integration errors by tracing root causes
  • Suggests concrete code fixes

Example: "I added a new MCP tool. Please use the mcp-validator agent to test it."

2. codebase-guide (Claude Sonnet 4.6)

Specialization: Deep expert on clodbridge's architecture and code patterns.

Use when:

  • Navigating an unfamiliar part of the codebase
  • Understanding how a feature was implemented
  • Asking about development conventions and patterns
  • Planning where to add new functionality
  • Debugging issues by understanding data flow

What it knows:

  • Reader layer architecture (parsing, discovery, file watching)
  • MCP tool/resource implementations
  • Testing patterns and test structure
  • Rule mode classification (always, auto-attached, agent-requested)
  • Key patterns (async iterables, path normalization, error handling)

Example: "Where should I add a new file type? Use the codebase-guide agent."

Git / delivery (user-global)

Cadence, batch_commit, verify-before-push: ~/.claude/skills/agent-deliver/SKILL.md and ~/.claude/skills/good-version-control/SKILL.md—do not duplicate that workflow in repo rules.

Read the full file on GitHub · 208 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 · 208 lines · 1,838 tokens per session scan A b0e849c186fc

Subscribe to this mod's changes

clodbridge AGENTS.md is an instructions file published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,838 tokens to every session, about $0.0092 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 2026-08-31.

Related

Other instructions, from other repositories