deep-research-plan

deep-research-plan is a command for Claude Code from axiomantic/spellbook. It costs 17 tokens per session (3,571 once invoked), scanned A, original, MIT.

A planning command that breaks a research brief into separate, independent search threads. A research brief is a written statement of what to find, including subjects, sources, and when the work is complete.

In plain words
What is it for?
Use it to divide a large research task, choose source types, set search limits, and define measurable completion criteria before investigation begins.
Why use it?
It prevents important subjects from being missed and gives each thread a clear stopping point. It also keeps planning separate from actually searching the web.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/axiomantic/spellbook/deep-research-plan
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

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 deep-research-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/deep-research-plan.svg)](https://agentmods.dev/commands/axiomantic/spellbook/deep-research-plan)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/deep-research-plan"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/deep-research-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,571 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.03571
Opus 5 $0.00009 $0.01785
Sonnet 5 $0.00003 $0.00714
Haiku 4.5 $0.00002 $0.00357

Measured 6d ago against content hash 816df64c3385, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deep-research-plan 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 6d 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.

commands/deep-research-plan.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 1: Research Planning

Invariant Principles

  1. Thread independence is non-negotiable: No two threads may share mutable state or depend on each other's intermediate output. Merge threads rather than allow dependencies.
  2. Planning does not search: This phase produces a plan. It does NOT execute any web searches, API calls, or source retrieval. All searching happens in Phase 2.
  3. Every subject gets coverage: Each entry in the Subject Registry must appear in at least one thread. Orphaned subjects are a planning failure.
  4. Round budgets are ceilings, not targets: Threads that converge early MUST stop. Spending rounds "because we budgeted them" wastes resources and dilutes signal.
  5. Explicit convergence: Every thread needs machine-checkable "done" criteria. "I feel like we have enough" is not convergence.

Purpose: Decompose a Research Brief (Phase 0 output) into a Research Plan: independent parallel threads, each with source strategies, round budgets, and convergence criteria. A round is one search-execute-extract cycle against a defined source type.

Before Phase 1 begins, verify:

  1. Research Brief exists at ~/.local/spellbook/docs/<project-encoded>/research-<topic>/research-brief.md
  2. Research Brief contains: research question, sub-questions, Subject Registry, scope boundaries, and confidence targets
  3. Phase 0 is marked complete

If any prerequisite fails: STOP. Return to Phase 0 (deep-research-interview).

Step 1: Thread Decomposition

Read the Research Brief. Decompose the research into independent parallel threads.

1.1 Decomposition Rules

  • Each thread addresses 1-3 related sub-questions from the Brief
  • Threads MUST be independent (no shared mutable state)
  • Each subject from the Subject Registry must be assigned to at least one thread
  • Maximum 5 threads (diminishing returns beyond this)
  • Minimum 1 thread (even trivial research needs structure)

Read the full file on GitHub · 350 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. 6d ago First seen · 350 lines · 17 tokens per session scan A 816df64c3385

Subscribe to this mod's changes

deep-research-plan is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 3,571 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 2026-08-31.