research-only

research-only is a skill for Claude Code from ao92265/claude-code-playbook. It costs 96 tokens per session (702 once invoked), scanned B, original, MIT.

A strict research-only mode in which the coding agent investigates and reports findings without editing project files.

In plain words
What is it for?
Use it when you want analysis, research, or a BMAD or Ralph research phase. The results are delivered as written findings rather than code changes.
Why use it?
It prevents an investigation from accidentally changing code or other project state.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; names the NotebookEdit tool.

Part of the playbook plugin — 48 skills, 4 hooks shipped together

Good fit Use it when you want analysis, research, or a BMAD or Ralph research phase. The results are delivered as written findings rather than code changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ao92265/claude-code-playbook/research-only
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.

Any agent
npx skills add ao92265/claude-code-playbook --skill research-only
Clone the repo
git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code.

Or install playbook, the plugin that ships this one along with the rest of its 48 skills, 4 hooks.

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-only

README.md
[![agentmods](https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/research-only.svg)](https://agentmods.dev/skills/ao92265/claude-code-playbook/research-only)
Your own site
<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/research-only"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/research-only.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 702 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00096 $0.00702
Opus 5 $0.00048 $0.00351
Sonnet 5 $0.00019 $0.00140
Haiku 4.5 $0.00010 $0.00070

Measured 8d ago against content hash 093716eda916, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

research-only scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The `research-only-guard.sh` PreToolUse hook (registered in `~/.claude/settings.json`) blocks `Edit`/`Write`/`NotebookEdit` whenever the sentinel file exists. This makes the guarantee mechanical, not just prose.
skills/research-only/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research-Only Mode

You are in strict research-only mode. The user wants findings, not changes.

Hard Rules

  1. NEVER use Edit, Write, MultiEdit, or NotebookEdit. Not once. Not "just this one small fix."
  2. NEVER run Bash commands that mutate state: no git commit, git push, npm install, rm, mv, redirects (>, >>), or anything that writes to disk — except the sentinel-file ops in the next section, which are required.
  3. Allowed tools only: Read, Grep, Glob, WebFetch, WebSearch, and read-only Bash (git log, git diff, git status, ls, cat, gh pr view, etc.).
  4. Deliver findings inline as markdown in your response. Do not create report files unless the user explicitly asks.
  5. Do not end your response with "want me to implement this?" or offer follow-up edits. Exit cleanly — the user will ask if they want implementation.

Sentinel-File Enforcement (mechanical guarantee)

The research-only-guard.sh PreToolUse hook (registered in ~/.claude/settings.json) blocks Edit/Write/NotebookEdit whenever the sentinel file exists. This makes the guarantee mechanical, not just prose.

On entry to this skill (very first action, before anything else):

mkdir -p .claude/state && touch .claude/state/research-only.flag

On clean exit (when the user explicitly ends research-only mode, or when the answer is delivered and the user is moving on):

rm -f .claude/state/research-only.flag

The flag is per-working-directory. If the user invokes the skill in a worktree, the flag lives in that worktree's .claude/state/. Do not write the flag at ~/.claude/state/ — the hook checks the CWD.

Pre-response Checklist

Before sending your final response, confirm:

  • I used zero Edit/Write/MultiEdit/NotebookEdit calls
  • I ran zero state-mutating Bash commands
  • My findings are delivered as markdown in the response
  • I am not offering unsolicited implementation

Why This Skill Exists

Read the full file on GitHub · 56 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. 8d ago First seen · 56 lines · 96 tokens per session scan B 093716eda916

Subscribe to this mod's changes

research-only is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 21d ago), licensed MIT. It adds 96 tokens to every session and 702 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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