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.
git clone --depth 1 https://github.com/bdiasti/maestro-bundle-clinpx agentmods add skills/bdiasti/maestro-bundle-cli/deep-agent-middlewareWrote 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.
[](https://agentmods.dev/skills/bdiasti/maestro-bundle-cli/deep-agent-middleware)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Use built-in middleware (TodoList, Filesystem, SubAgent, Summarization)
- Create custom middleware with
@wrap_tool_call - Chain multiple middleware
- 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)
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.
- 2mo ago First seen · 132 lines · 39 tokens per session scan A 7fa63d84bf4d
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.
deep-agent-middleware compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-agent-middlewarebdiasti/maestro-bundle-cli | Skill | 22 | 7mo ago | MIT | A | 39 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 6d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |