A coding guide for deepcrew-ai, a Python library for running one or more AI agents and coordinating their work.

Use it to add AI agents to Python projects, connect model providers, build dependent pipelines, process images or PDFs, stream results, or require approval for tool use.

It helps you choose the right setup for a single agent, parallel agents, fixed workflows, self-review loops, or delegated tasks.

How Aayush-Joshi-01/deepcrew-ai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Aayush-Joshi-01/deepcrew-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Aayush-Joshi-01/deepcrew-ai/main/.claude/skills/deepcrew/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Aayush-Joshi-01/deepcrew-ai

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aayush-joshi-01/deepcrew-ai/deepcrew/github.svg)](https://agentmods.dev/skills/aayush-joshi-01/deepcrew-ai/deepcrew)

Your own site

<a href="https://agentmods.dev/skills/aayush-joshi-01/deepcrew-ai/deepcrew"><img src="https://agentmods.dev/badge/skills/aayush-joshi-01/deepcrew-ai/deepcrew/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aayush-joshi-01/deepcrew-ai/deepcrew"><img src="https://agentmods.dev/badge/skills/aayush-joshi-01/deepcrew-ai/deepcrew.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,614 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.

Model	Per session	Once invoked
Fable 5.1	$0.00107	$0.02614
Opus 5.5	$0.00043	$0.01046
Sonnet 5.5	$0.00021	$0.00523
Haiku 4.5	$0.00011	$0.00261

Measured 12d ago against content hash 73a692f3de04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deepcrew 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 12d 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.

.claude/skills/deepcrew/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deepcrew-ai integration skill

deepcrew-ai is an async, LiteLLM-backed multi-agent library. This skill teaches you how to wire it into any Python project correctly on the first try.

Install

pip install deepcrew-ai
# optional extras:
pip install deepcrew-ai[fastapi]   # SSE streaming endpoint
pip install deepcrew-ai[redis]     # Redis-backed memory
pip install deepcrew-ai[otel]      # OpenTelemetry tracing
pip install deepcrew-ai[log]       # colour logging via rich (plain ANSI fallback without it)

API keys are read by LiteLLM from standard env vars — set whichever providers you use: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, etc. The model string on every Agent determines the provider, e.g. "openai/gpt-4o", "anthropic/claude-opus-4-8", "gemini/gemini-2.0-flash", "ollama/llama3.2" (local, no key needed).

Decision table

You need...	Use
One agent, no coordination	`Agent` + `run_agent()`
Router picks one agent or fans out to several in parallel	`Orchestrator`
An explicit, fixed pipeline of steps with dependencies	`WorkflowBuilder`
An agent that critiques and improves its own answer	`Agent(loop_config=LoopConfig(verifier=...))`
An agent that recalls relevant past runs before answering	`Agent(episodic_memory=EpisodicMemory(...))`
An agent that accumulates reusable how-to strategies	`Agent(procedural_memory=ProceduralMemory(...))` + a verifier loop
An agent that can delegate sub-tasks to fresh agents mid-run	`Orchestrator(enable_spawn=True)`
A simple chatbot UI that should only show the reply text	`StreamPolicy.chat()`
A technical/debug UI that should show everything	`StreamPolicy.verbose()`
Approve or block individual tool calls before they run	`AgentHooks(approve_tool=...)`

Recipes

Single agent + tool

from deepcrew import Agent, run_agent, tool


@tool
def get_weather(city: str) -> str:
    """Look up the current weather for a city."""
    return f"Sunny in {city}"


agent = Agent(name="assistant", model="openai/gpt-4o", tools=[get_weather])
result = await run_agent(agent, [{"role": "user", "content": "Weather in Tokyo?"}])
print(result.text)

Read the full file on GitHub · 269 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.

12d ago Changed · +70 lines 73a692f3de04
2mo ago First seen · 199 lines · 107 tokens per session scan A 978a6e1949b0

Subscribe to this mod's changes

deepcrew is a skill published in the GitHub repository Aayush-Joshi-01/deepcrew-ai (3 stars, last pushed 13d ago), licensed MIT. It adds 107 tokens to every session and 2,614 once invoked, about $0.0004 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 2026-08-31.

Autonomous Agents Building agents agent-framework agentic-ai ai-agents anthropic asyncio

deepcrew next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deepcrewAayush-Joshi-01/deepcrew-ai	Skill	3	13d ago	MIT	A	107	Claude Code
openacme-platformsandydasari/openacme	Skill	89	3mo ago	MIT	A	66	Claude Code, Codex
coding-conventionssandydasari/openacme	Skill	89	3mo ago	MIT	A	27	Claude Code, Codex
hive.browser-automationaden-hive/hive	Skill	11k	today	Apache-2.0	A	142	Claude Code, Codex
hive.linkedin-automationaden-hive/hive	Skill	11k	today	Apache-2.0	A	99	Claude Code, Codex
hive.worker-delegationaden-hive/hive	Skill	11k	today	Apache-2.0	A	58	Claude Code, Codex
hive.x-automationaden-hive/hive	Skill	11k	today	Apache-2.0	A	81	Claude Code, Codex

deepcrew-ai: Skill for Claude Code