research-first

research-first is a skill for Claude Code from evanmcgoogan/skin-in-the-game. It costs 105 tokens per session (406 once invoked), scanned A, original, MIT.

A development workflow that requires the agent to study an unfamiliar codebase before editing it and verify changes against real behavior afterward.

In plain words
What is it for?
Use it before implementing features or modifying existing code, especially when you need to trace patterns, data flow, constraints, and one-way design decisions.
Why use it?
It reduces changes based on incorrect assumptions and makes it clearer when something was not actually tested.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skin-in-the-game plugin — 6 skills, 1 hook shipped together

Good fit Use it before implementing features or modifying existing code, especially when you need to trace patterns, data flow, constraints, and one-way design decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evanmcgoogan/skin-in-the-game/research-first
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 evanmcgoogan/skin-in-the-game --skill research-first
Clone the repo
git clone --depth 1 https://github.com/evanmcgoogan/skin-in-the-game

Made for: Claude Code.

Or install skin-in-the-game, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/research-first/github.svg)](https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/research-first)
Your own site
<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/research-first"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/research-first/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-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/research-first"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/research-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 406 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 $0.00105 $0.00406
Opus 5 $0.00053 $0.00203
Sonnet 5 $0.00021 $0.00081
Haiku 4.5 $0.00011 $0.00041

Measured 11d ago against content hash 50f2cf82d7d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-first 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.

skills/research-first/SKILL.md · 24 lines

What it actually says

Research First

Measure twice, cut once. The two-week disaster — confidently building the wrong thing — almost always traces back to cutting before understanding the surface. Reading is cheap; rework is not. (Principle 8.)

Before you write

  • Read the relevant code first. Find the existing patterns, conventions, and constraints. Your change should read like the surrounding code wrote it (Principle 9).
  • Find the real shape of the problem. Trace how the thing works today before changing how it works tomorrow. Grep for the symbol; read the call sites; follow the data flow.
  • Locate the one-way doors — the parts expensive to change later (data model, public interface) — and design those deliberately.

While you build

Match what's there. New invention is a liability when a convention already exists (Principle 9). Prefer the smallest change that fits.

Before you call it done

  • Verify against real behavior, not against your own expectation. Run it. Read the output. Exercise the path you changed.
  • If you couldn't verify something, say so plainly — never imply a pass you didn't observe (Principle 5; see reality-check).

The test

Understand the surface before you cut into it, and verify what you built before you call it done. If you haven't read it, you don't yet know enough to change it.

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 · 24 lines · 105 tokens per session scan A 50f2cf82d7d1

Subscribe to this mod's changes

research-first is a skill published in the GitHub repository evanmcgoogan/skin-in-the-game (1 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 406 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

delegate

Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.

PyModel/claude-architect · 47 tokens

codex

Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.

PyModel/claude-architect · 31 tokens

commit

A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.

restarter/lets-workflow · 90 tokens

orient

Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.

restarter/lets-workflow · 42 tokens

x-multi-llm-align

A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.

KtKID/x-dev-pipeline · 293 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens