spec-spine: Skill for Claude Code

.claude/skills/research/SKILL.md

research is a skill for Claude Code from statecrafting/spec-spine. It costs 33 tokens per session (947 once invoked), scanned A, original, Apache-2.0.

A research workflow that classifies a question and assigns a small number of specialised AI agents to investigate it in parallel or in depth. It uses project specifications and code for internal questions, and web searches for outside topics.

In plain words
What is it for?
It is for factual lookups, broad surveys, detailed topic research, codebase questions, specification tracing, and research based on external documentation or papers.
Why use it?
It prevents every question from receiving the same costly investigation and keeps research reports in files rather than passing all of them through the conversation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

This is statecrafting/spec-spine's own configuration. It tells Claude Code how to work on spec-spine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spec-spine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to statecrafting/spec-spine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/statecrafting/spec-spine/main/.claude/skills/research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/statecrafting/spec-spine

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 research

README.md
[![agentmods](https://agentmods.dev/badge/skills/statecrafting/spec-spine/research/github.svg)](https://agentmods.dev/skills/statecrafting/spec-spine/research)
Your own site
<a href="https://agentmods.dev/skills/statecrafting/spec-spine/research"><img src="https://agentmods.dev/badge/skills/statecrafting/spec-spine/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 research

Your own site · 80×15
<a href="https://agentmods.dev/skills/statecrafting/spec-spine/research"><img src="https://agentmods.dev/badge/skills/statecrafting/spec-spine/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 947 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 $0.00033 $0.00947
Opus 5 $0.00016 $0.00474
Sonnet 5 $0.00007 $0.00189
Haiku 4.5 $0.00003 $0.00095

Measured yesterday against content hash 6a5c3d232531, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude/skills/research/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research

Conduct deep, parallel research on a topic using specialized sub-agents. Agents cost tokens: classify first, spawn the fewest that answer the question, and pass reports through files rather than inline.

Research query

$ARGUMENTS

Phase 1: classify

Type Characteristics Sub-agents Depth each
Breadth-first several independent aspects, surveys, comparisons 3 to 6 5 to 10 searches
Depth-first one topic needing thorough understanding 2 to 3 10 to 15 searches
Simple factual one fact, one lookup 1 3 to 5 searches

Decide: query type, agent count, domains (corpus, codebase, external docs, papers, general web), and scope (corpus-only, web-only, hybrid).

  • Corpus questions ("what does spec 020 say about erasure", "who owns this file", "what depends on 064", "how does the compiler validate frontmatter"): use the explorer agent with spec-spine registry show|relationships <id>, spec-spine index render, spec-spine index coverage, Grep over specs/ and the source, and git log. Never parse .derived/ directly.
  • External questions (a protocol, a library's semantics, an RFC): WebSearch and WebFetch, preferring primary sources (specifications, RFCs, the library's own docs).
  • Many questions are hybrid; split them across agents by domain.

Phase 2: parallel execution

Spawn all sub-agents in one message. Each prompt begins with a depth trigger: "Quick check:", "Investigate:", or "Deep dive:".

Each sub-agent MUST write its full report to the session scratchpad directory when one is listed in the system prompt (otherwise a research/ directory under the tool-state root spec-spine.toml [layout] state_dir names, never committed) as research_<timestamp>_<slug>.md and return only: the file path, a two to three sentence summary, key topics, and the source count.

Example, hybrid ("how should the new spec bind an identity key to the transport certificate?"):

Task 1: "Deep dive: raw public key TLS (RFC 7250) support in the libraries this stack uses"
Task 2: "Investigate: what the existing specs already fix about identity binding; use spec-spine registry show and relationships"

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 33 tokens per session scan A 6a5c3d232531

Subscribe to this mod's changes

research is a skill published in the GitHub repository statecrafting/spec-spine (10 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 947 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 2026-09-07.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens