A project-planning analysis that sends the work to three specialist roles: a researcher, an architect, and a product manager. It combines their findings into a prioritized report about what to build next.

Use it to inspect a project's current state, investigate code and outside factors, compare possible improvements, and produce a ranked plan for the next work.

It gives a project several focused viewpoints instead of relying on one general review. The result helps separate code-health issues, external signals, and product priorities.

deepdive — Skill for Claude Code and Codex by yimwoo: A project-planning analysis that sends the work to three…

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 skills/yimwoo/codex-agenteam/deepdive

Any agent

npx skills add yimwoo/codex-agenteam --skill deepdive

Clone the repo

git clone --depth 1 https://github.com/yimwoo/codex-agenteam

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yimwoo/codex-agenteam/deepdive.svg)](https://agentmods.dev/skills/yimwoo/codex-agenteam/deepdive)

Your own site

<a href="https://agentmods.dev/skills/yimwoo/codex-agenteam/deepdive"><img src="https://agentmods.dev/badge/skills/yimwoo/codex-agenteam/deepdive.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,825 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01825
Opus 5	$0.00017	$0.00912
Sonnet 5	$0.00007	$0.00365
Haiku 4.5	$0.00003	$0.00183

Measured 5d ago against content hash a21ca9f120fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

deepdive 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 5d 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.

skills/deepdive/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgenTeam Deepdive

Run a full specialist analysis by dispatching three roles in parallel. Unlike the standup skill (which reads state locally), deepdive launches Codex subagents to investigate external signals, internal code health, and strategic priorities. Expect 30-60 seconds for completion.

Process

1. Auto-Init Guard

Check for .agenteam/config.yaml, .agenteam.team/config.yaml, or legacy agenteam.yaml in the project root. If all are missing:

Create config dir: mkdir -p .agenteam
Copy the template: cp <plugin-dir>/templates/agenteam.yaml.template .agenteam/config.yaml
Set the team name to the project directory name
Generate agents: python3 <runtime>/agenteam_rt.py generate
Tell the user: "AgenTeam auto-initialized with default roles. Edit .agenteam/config.yaml to customize."

2. Gather State with Dispatch Flag

Call the runtime with the --dispatch flag to get state and dispatch plans for the three specialist roles:

python3 <runtime>/agenteam_rt.py standup --dispatch

Capture the JSON output. Expected fields (same as standup, plus dispatch info):

health -- on-track, at-risk, off-track, or no-active-run
run_id -- current run identifier (may be null)
task -- task description
stages -- stage statuses
artifact_paths -- map of role name to artifact directory
output_path -- where to write the final report (e.g., docs/meetings/<timestamp>-deepdive.md)
dispatch -- list of {role, agent} objects for the three specialist roles (researcher, architect, pm)

Create a durable checkpoint at .agenteam/deepdive/<run_id>.json before dispatch. Record max_elapsed_minutes (default 60), max_agents (default 2 concurrent specialists), each role's attempt/thread ID, last heartbeat, output artifact, and stop reason. On restart, validate completed artifacts and resume only missing or interrupted roles; never repeat a completed specialist solely because the controller restarted.

3. Dispatch Specialist Agents in Parallel

Read the full file on GitHub · 236 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.

5d ago First seen · 236 lines · 34 tokens per session scan A a21ca9f120fa

Subscribe to this mod's changes

deepdive is a skill published in the GitHub repository yimwoo/codex-agenteam (13 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,825 once invoked, about $0.0002 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 2026-08-30.

LLM Multi-Agent Planning Research ai-agents codex developer-tools openai

oh-my-dynamic

Multi-agent orchestration engine for complex tasks. Use when you need to break a complex query into subtasks, run them in parallel with a DAG engine, and synthesize results. Triggers on: multi-agent, parallel execution, orchestrate, DAG, decompose task, dynamic workflow.

PIGU-PPPgu/oh-my-Dynamic · 63 tokens

multi-agent-run

Run a multi-agent workflow on any complex task. One command to decompose, parallelize, and synthesize. Triggers on: run agents, parallel analysis, multi-agent, decompose and run, orchestrate task.

PIGU-PPPgu/oh-my-Dynamic · 49 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

implementation-final-review

Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…

openai/openai-agents-python · 58 tokens

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens