readonly-research

readonly-research is a skill for Claude Code from davila7/claude-with-skills. It costs 31 tokens per session (523 once invoked), scanned A, original, MIT.

A read-only method for researching how a codebase works and answering a specific question. It searches relevant files, callers, tests, configuration, and documentation without changing files or running builds.

In plain words
What is it for?
Use it to understand architecture, trace a feature or function, investigate behavior, or answer codebase questions before making changes.
Why use it?
It provides a structured way to investigate existing code while keeping the repository untouched. Tests and related code can reveal the intended behavior.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to understand architecture, trace a feature or function, investigate behavior, or answer codebase questions before making changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davila7/claude-with-skills/readonly-research
About the project

Claude With Skills is a progressive course that teaches developers to create reusable, portable Agent Skills for Claude Code, from basic SKILL.md files to advanced automation and plugin packaging. It is intended for developers who want repeatable instructions and workflows instead of repeatedly pasting the same guidance. The catalogue contains the course's skills, agents, and instruction.

davila7/claude-with-skills · 12 stars · on GitHub · claude-with-skills.vercel.app

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 davila7/claude-with-skills --skill readonly-research
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-with-skills

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 readonly-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/davila7/claude-with-skills/readonly-research/github.svg)](https://agentmods.dev/skills/davila7/claude-with-skills/readonly-research)
Your own site
<a href="https://agentmods.dev/skills/davila7/claude-with-skills/readonly-research"><img src="https://agentmods.dev/badge/skills/davila7/claude-with-skills/readonly-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 readonly-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/davila7/claude-with-skills/readonly-research"><img src="https://agentmods.dev/badge/skills/davila7/claude-with-skills/readonly-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 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 $0.00031 $0.00523
Opus 5 $0.00015 $0.00262
Sonnet 5 $0.00006 $0.00105
Haiku 4.5 $0.00003 $0.00052

Measured 11d ago against content hash 6cc9ebba24ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

readonly-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 11d 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.

src/content/docs/02-intermediate/lesson-03-allowed-tools/examples/readonly-research/SKILL.md · 53 lines

What it actually says

Codebase research

Research the codebase to answer the question or complete the investigation. Do not modify any files. Do not create files. Do not run tests or build commands.

Step 1: Clarify the question

If $ARGUMENTS is empty or ambiguous, state the research question you are answering before proceeding. If the question is clear, proceed directly.

Step 2: Search for relevant files

Start broad, then narrow. Use a combination of approaches:

  • grep -r "<term>" --include="*.ts" --include="*.js" -l to find files containing a keyword
  • glob("src/**/*.ts") or similar to list files in a known area
  • find . -name "<filename>" -not -path "*/node_modules/*" for specific filenames

Search for the primary concept, then for related symbols, then for tests that exercise the relevant code.

Step 3: Read the most relevant files

Read the files that are most likely to answer the question. Prioritize:

  1. The module or function directly named in the question
  2. Its callers and dependents (to understand how it is used)
  3. Its tests (to understand expected behavior)
  4. Any relevant configuration or type definitions

Avoid reading files speculatively. Only read a file if there is a specific reason it could answer the question.

Step 4: Check git history if relevant

If the question is about why something is the way it is, or when a change was made, use:

git log --oneline --follow -20 <file>
git show <commit-hash>

Step 5: Synthesize findings

Present a clear answer to the research question with:

  • The specific answer (yes/no, the function name, the file path, etc.)
  • Supporting evidence with file:line references for every specific claim
  • Areas of uncertainty: files you could not access, code paths you could not trace, or ambiguities in the implementation

Format the response for the user's question, not as a generic research report. If the user asked "where is the auth logic?", answer that directly, then provide supporting detail.

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. 11d ago First seen · 53 lines · 31 tokens per session scan A 6cc9ebba24ff

Subscribe to this mod's changes

readonly-research is a skill published in the GitHub repository davila7/claude-with-skills (12 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 523 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 2026-08-30.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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