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.
npx agentmods add commands/axiomantic/spellbook/deep-research-plangit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/commands/axiomantic/spellbook/deep-research-plan)<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>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 | $0.00017 | $0.03571 |
| Opus 5 | $0.00009 | $0.01785 |
| Sonnet 5 | $0.00003 | $0.00714 |
| Haiku 4.5 | $0.00002 | $0.00357 |
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.
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
- 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.
- 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.
- Every subject gets coverage: Each entry in the Subject Registry must appear in at least one thread. Orphaned subjects are a planning failure.
- Round budgets are ceilings, not targets: Threads that converge early MUST stop. Spending rounds "because we budgeted them" wastes resources and dilutes signal.
- 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:
- Research Brief exists at
~/.local/spellbook/docs/<project-encoded>/research-<topic>/research-brief.md - Research Brief contains: research question, sub-questions, Subject Registry, scope boundaries, and confidence targets
- 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)
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.
- 6d ago First seen · 350 lines · 17 tokens per session scan A 816df64c3385
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.
Other commands, from other repositories
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
add-command
Add a new slash command to the current plugin.