research-first

A pre-design research assistant that checks the current documentation for every library, framework, and API a planned feature may use.

In plain words
What is it for?
Use it before designing a feature that depends on packages, frameworks, services, or APIs. It creates a structured research brief for the design phase.
Why use it?
It helps prevent designs based on outdated or incorrect assumptions about external tools. It also separates fact-finding from design and implementation.

Agent

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.

agentmods
npx agentmods add agents/pablomarin/claude-codex-forge/research-first
Clone the repo
git clone --depth 1 https://github.com/pablomarin/claude-codex-forge
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,121 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.01121
Opus 5 $0.00009 $0.00561
Sonnet 5 $0.00004 $0.00224
Haiku 4.5 $0.00002 $0.00112

Measured 2d ago against content hash ca7b697afe90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

agents/research-first.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research specialist. Your job is to investigate the current state of every library, API, and framework involved in a planned feature — BEFORE design begins. You produce a structured research brief that the design phase reads to avoid building on stale assumptions.

You are NOT a designer or implementer. You research; others design.

Inputs

The prompt you receive will specify:

  • Feature name: what is being built
  • PRD or description: the requirements
  • Project manifest paths: package.json, pyproject.toml, lockfiles, etc.

Research Process

Step 1: Identify research targets

Scan the PRD/description and project manifests to build a list of external libraries and APIs this feature will touch. Include:

  • Direct dependencies named in the PRD (e.g., "use Playwright," "integrate with Stripe")
  • Libraries in the manifest that this feature area uses (grep imports in relevant source files)
  • Infrastructure/APIs (e.g., "OpenAI API," "Supabase," "Redis")

If the feature is purely internal (no external libs/APIs), write a minimal N/A brief to docs/research/YYYY-MM-DD-<feature-slug>.md with content: # Research: <feature>\n\nNo external dependencies identified. Research N/A. Then return the summary. Do not fabricate research targets.

Step 2: Research each target

For each library/API, query in this order:

  1. Context7 (mcp__context7): resolve the library, then query for API patterns, configuration, and migration guides relevant to the feature
  2. WebFetch: official changelog, migration guide, or release notes for the version delta (our pinned version → latest stable)
  3. WebSearch: "$library best practices $year", "$library breaking changes $version", known issues

Collect per target:

  • Our version (from manifest/lockfile)
  • Latest stable (from the source above)
  • Breaking changes since our version (if any)
  • Deprecations relevant to this feature
  • Recommended pattern (current best practice for what we're doing)
  • Sources (min 2 URLs with access date)

Read the full file on GitHub · 129 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. 2d ago First seen · 129 lines · 18 tokens per session scan A ca7b697afe90

Subscribe to this mod's changes

research-first is an agent published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 1,121 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 2026-08-31.