speckit.spex-teams.research

speckit.spex-teams.research is a command for Claude Code from rhuss/cc-spex. It costs 11 tokens per session (1,445 once invoked), scanned A, original, Apache-2.0.

A planning command that explores different parts of a codebase in parallel using Claude Code Agent Teams. It gathers the findings and uses them to prepare a more informed implementation plan.

In plain words
What is it for?
Use it when planning a change that requires research across multiple parts of a repository.
Why use it?
It reduces the need for one session to inspect every relevant file sequentially before planning. Without the required team setting, it falls back to research in one session.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it when planning a change that requires research across multiple parts of a repository.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rhuss/cc-spex/speckit.spex-teams.research
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.

Clone the repo
git clone --depth 1 https://github.com/rhuss/cc-spex

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.

agentmods badge for speckit.spex-teams.research

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-teams.research/github.svg)](https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-teams.research)
Your own site
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-teams.research"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-teams.research/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 speckit.spex-teams.research

Your own site · 80×15
<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex-teams.research"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex-teams.research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,445 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 $0.00011 $0.01445
Opus 5 $0.00005 $0.00723
Sonnet 5 $0.00002 $0.00289
Haiku 4.5 $0.00001 $0.00145

Measured 10d ago against content hash 13fa32d6c6da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit.spex-teams.research 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 10d 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.

specs/038-neutral-command-vocab/pre-rewrite-snapshot/spex-teams/commands/speckit.spex-teams.research.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teams Research: Parallel Codebase Exploration for Planning

Overview

This command orchestrates parallel codebase research using Claude Code Agent Teams during the plan phase. The lead session analyzes the spec to identify research topics, spawns research agents to explore different parts of the codebase simultaneously, collects their findings, and then generates the plan with comprehensive codebase knowledge.

Prerequisites

CC Teams Feature Flag

Check if Agent Teams is enabled:

# Check settings.local.json for the feature flag
FLAG=$(jq -r '.env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS // ""' .claude/settings.local.json 2>/dev/null)

If the flag is not set ("" or missing):

  1. Set it in .claude/settings.local.json:
    jq '.env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS = "1"' .claude/settings.local.json > /tmp/settings.json && mv /tmp/settings.json .claude/settings.local.json
    
  2. Inform the user: "Agent Teams feature flag has been enabled. Please restart Claude Code for teams to activate."
  3. Fall back to single-session research for this session (teams will work on next run).

If the flag is set: Proceed with team research.

Phase 1: Research Topic Identification

Read the spec.md and identify what codebase knowledge is needed to create a solid plan.

Identify Research Areas

From the spec, extract:

  1. Existing code to modify: Which files, modules, or packages does the spec reference or affect?
  2. Patterns to follow: What existing patterns in the codebase should the plan adopt?
  3. Integration points: Where does the new feature connect to existing code?
  4. Technology questions: What libraries, frameworks, or tools are already in use that are relevant?

Group into Independent Research Topics

Organize the areas into independent research topics that can be explored in parallel. Each topic should be:

  • Self-contained: An agent can research it without needing results from other topics
  • Focused: Specific enough to produce actionable findings (not "explore the whole codebase")
  • Relevant: Directly needed for plan creation

Read the full file on GitHub · 164 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. 10d ago First seen · 164 lines · 11 tokens per session scan A 13fa32d6c6da

Subscribe to this mod's changes

speckit.spex-teams.research is a command published in the GitHub repository rhuss/cc-spex (117 stars, last pushed 22d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,445 once invoked, about $0.0001 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.