feature-research

feature-research is a command for Claude Code from axiomantic/spellbook. It costs 19 tokens per session (4,058 once invoked), scanned A, original, MIT.

A command for researching a feature before asking detailed questions or writing an implementation plan. It explores the codebase, detects unclear requirements, and records factual findings.

In plain words
What is it for?
Use it to inspect relevant code, identify unknowns and ambiguities, and prepare evidence for the feature-discovery phase.
Why use it?
It reduces the chance of designing a change without understanding the existing systems or the request. A prerequisite check prevents this phase from being skipped when research is needed.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run scripts/check_research_quality.py ~/.local/spellbook/docs/<project-encoded>/research/research-[feature-slug]-[timestamp].json.

Good fit Use it to inspect relevant code, identify unknowns and ambiguities, and prepare evidence for the feature-discovery phase.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook
agentmods
npx agentmods add commands/axiomantic/spellbook/feature-research

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 feature-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-research/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/feature-research)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-research"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-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 feature-research

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-research"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,058 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 $0.00019 $0.04058
Opus 5 $0.00010 $0.02029
Sonnet 5 $0.00004 $0.00812
Haiku 4.5 $0.00002 $0.00406

Measured 6d ago against content hash ecd282e6a4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feature-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 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/feature-research.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Research (Phase 1)

Before ANY Phase 1 work begins, run this verification:

# ══════════════════════════════════════════════════════════════
# PREREQUISITE CHECK: feature-research (Phase 1)
# ══════════════════════════════════════════════════════════════

echo "=== Phase 1 Prerequisites ==="

# CHECK 1: This phase runs only when the needs_research flag is set.
# needs_research = "the work touches code/systems we don't yet understand,
# OR the requirements themselves are still fuzzy." It is the single operator
# flag (chosen in Phase 0) that switches on BOTH Research (Phase 1) and
# Discovery (Phase 1.5). See SESSION_PREFERENCES.need_flags.
echo "Required: need_flags.needs_research == true"
echo "Current needs_research: [SESSION_PREFERENCES.need_flags.needs_research]"
# If needs_research is false, this phase does not run — develop skips
# Research and Discovery and proceeds with the phases its other flags select.

# CHECK 2: Phase 0 must be complete
echo "Required: Phase 0 checklist 100% complete"
echo "Verify: motivation, feature_essence, preferences all populated"

# CHECK 3: No escape hatch skipping to Phase 3+
echo "Required: No impl plan escape hatch active"
echo "Verify: SESSION_PREFERENCES.escape_hatch.type != 'impl_plan'"

If ANY check fails: STOP. Do not proceed. Return to the appropriate phase.

Anti-rationalization: Tempted to skip because "you already know needs_research is set" or "Phase 0 was obviously complete"? That is Pattern 2 (Expertise Override). Run the check. It takes 5 seconds.

Invariant Principles

  1. Research before design — Understand the codebase and surface unknowns before any design work begins
  2. The gate is an exit status, not a scorecheck_research_quality.py blocks on the artifact; confidence ratings are self-assessed and labelled as such; bypass requires explicit user consent
  3. Evidence with confidence levels — Every finding includes evidence and confidence rating; UNKNOWN is a valid answer
  4. Ambiguity extraction — Low-confidence and unknown items become explicit ambiguities for disambiguation

Read the full file on GitHub · 385 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 · 385 lines · 19 tokens per session scan A ecd282e6a4f3

Subscribe to this mod's changes

feature-research is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 4,058 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 2026-09-03.