deep-agent-middleware

deep-agent-middleware is a skill for Claude Code, Codex from bdiasti/maestro-bundle-cli. It costs 39 tokens per session (918 once invoked), scanned A, original, MIT.

A setup guide for middleware in Deep Agents. Middleware is code that runs around tool calls, allowing you to observe, check, limit, or change what happens when a tool is used.

In plain words
What is it for?
Use it to log tool calls, validate inputs, limit API requests, intercept tool execution, and combine built-in or custom middleware.
Why use it?
It lets you apply shared rules to many tools in one place instead of adding separate logging, validation, or rate-limit code to every tool.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python agent/main.py 2>&1 | grep "[TOOL]".

Good fit Use it to log tool calls, validate inputs, limit API requests, intercept tool execution, and combine built-in or custom middleware.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/bdiasti/maestro-bundle-cli
agentmods
npx agentmods add skills/bdiasti/maestro-bundle-cli/deep-agent-middleware

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for deep-agent-middleware

README.md
[![agentmods](https://agentmods.dev/badge/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware/github.svg)](https://agentmods.dev/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware)
Your own site
<a href="https://agentmods.dev/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware"><img src="https://agentmods.dev/badge/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware/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.

agentmods 80×15 button for deep-agent-middleware

Your own site · 80×15
<a href="https://agentmods.dev/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware"><img src="https://agentmods.dev/badge/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00918
Opus 5.5 $0.00016 $0.00367
Sonnet 5.5 $0.00008 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 2mo ago against content hash 7fa63d84bf4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deep-agent-middleware 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 2mo 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.

templates/bundle-ai-agents-deep/skills/deep-agent-middleware/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Agent Middleware

Add cross-cutting concerns to Deep Agents with built-in and custom middleware for logging, validation, rate limiting, and tool interception.

When to Use

  • When you need to log all tool calls
  • When you need to validate inputs before tools execute
  • When you need rate limiting on API calls
  • When you need custom behavior around tool execution

Available Operations

  1. Use built-in middleware (TodoList, Filesystem, SubAgent, Summarization)
  2. Create custom middleware with @wrap_tool_call
  3. Chain multiple middleware
  4. Add conditional middleware

Multi-Step Workflow

Step 1: Understand Built-in Middleware

These are automatically active:

Middleware What it does Can disable?
TodoListMiddleware write_todos tool for planning No
FilesystemMiddleware ls, read_file, write_file, etc. No
SubAgentMiddleware task tool for delegation No
SummarizationMiddleware Compresses long conversations No
AnthropicPromptCachingMiddleware Token optimization for Anthropic Auto
PatchToolCallsMiddleware Repairs broken tool calls Auto

Step 2: Create Custom Middleware

# agent/middleware.py
from langchain.agents.middleware import wrap_tool_call
import time
import logging

logger = logging.getLogger(__name__)

@wrap_tool_call
def log_tool_calls(request, handler):
    """Log every tool call with timing."""
    start = time.time()
    logger.info(f"[TOOL] {request.name} called with: {request.args}")

    result = handler(request)

    duration = time.time() - start
    logger.info(f"[TOOL] {request.name} completed in {duration:.2f}s")
    return result

@wrap_tool_call
def validate_file_paths(request, handler):
    """Prevent access to sensitive files."""
    if request.name in ("read_file", "write_file", "edit_file"):
        path = request.args.get("path", "")
        blocked = [".env", "secrets", "credentials", ".git/config"]
        if any(b in path for b in blocked):
            return f"Access denied: {path} is a protected file"

    return handler(request)

@wrap_tool_call
def rate_limit_api_calls(request, handler):
    """Rate limit external API calls."""
    api_tools = ["internet_search", "call_api"]
    if request.name in api_tools:
        time.sleep(1)  # Simple rate limit

    return handler(request)

Read the full file on GitHub · 132 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. 2mo ago First seen · 132 lines · 39 tokens per session scan A 7fa63d84bf4d

Subscribe to this mod's changes

deep-agent-middleware is a skill published in the GitHub repository bdiasti/maestro-bundle-cli (22 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 918 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

deep-agent-middleware compared with skills from other repositories

deep-agent-middleware next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deep-agent-middlewarebdiasti/maestro-bundle-cliSkill227mo agoMITA39Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80k6d agoMITA200Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex