What is recallchecker CLAUDE.md?

A set of Claude Code instructions for RecallChecker, a web tool and MCP server that answers whether a vehicle is recalled using U.S. government data. MCP is a way for software tools to provide data and actions to AI agents.

Use it when building or changing RecallChecker, especially its Next.js web app, Cloudflare deployment, cache, or shared recall-lookup logic.

It explains the project’s structure and requires the website and server to share one recall-lookup module instead of duplicating it.

How ollo12-prog/recallchecker configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ollo12-prog/recallchecker. 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/ollo12-prog/recallchecker/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ollo12-prog/recallchecker

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ollo12-prog/recallchecker/claude-md/github.svg)](https://agentmods.dev/instructions/ollo12-prog/recallchecker/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ollo12-prog/recallchecker/claude-md"><img src="https://agentmods.dev/badge/instructions/ollo12-prog/recallchecker/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ollo12-prog/recallchecker/claude-md"><img src="https://agentmods.dev/badge/instructions/ollo12-prog/recallchecker/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 892 This file is loaded in full into every session.

When invoked 892 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00892	$0.00892
Opus 5.5	$0.00357	$0.00357
Sonnet 5.5	$0.00178	$0.00178
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash a4d9ca78c9a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

recallchecker CLAUDE.md 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 2mo 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — RecallChecker

Instructions for Claude Code sessions in this repo. See README.md for what the project does and ROADMAP.md for build status.

What this is

A free web tool + reference pages + MCP server answering "Is this vehicle recalled?" using the keyless U.S. NHTSA recalls API. Three surfaces share one lookup core.

Tech stack

Framework: Next.js (App Router) + React, TypeScript.
Hosting: Cloudflare Workers via the OpenNext adapter (@opennextjs/cloudflare) — both the web app and the MCP server (a second Worker). Not Cloudflare Pages (its Next.js adapter is deprecated/Edge-only); OpenNext on Workers gives the full Node.js runtime + App Router.
Cache: Workers KV, behind a runtime-agnostic cache port (memory fallback in dev/test).
No database, no auth, no payments. Stateless lookups + cached responses.

Build with next build --webpack — Next's Turbopack output triggers a ChunkLoadError under OpenNext.

Architecture rule (important)

The recall-lookup logic lives in ONE shared module at src/lib/recalls/ (imported as @/lib/recalls). The website and the MCP server both import it — never duplicate lookup logic. Normalize every data source into a single Recall shape so the UI and the MCP tool are source-agnostic.

index.ts is the runtime-agnostic barrel — import this from the MCP Worker.
server.ts is OpenNext-coupled (getCloudflareContext) — web app only.

Data source

NHTSA Recalls API — api.nhtsa.gov/recalls/recallsByVehicle?make=&model=&modelYear=. No API key. Date format DD/MM/YYYY. Quirk: it intermittently returns HTTP 400 for valid no-match queries with a {Count:0,results:[]} body — treat the body as authoritative for 2xx and that 400, but let 5xx fail so an outage isn't masked as "no recalls."
Always display the data's "as of" date and a link to the official NHTSA notice. Data sourced from NHTSA (nhtsa.gov).

Conventions

Verify any external API behavior, prices, or availability live before relying on it — don't trust assumptions about a third-party API's shape.
Keep scope tight; validate the data source before building UI (see ROADMAP Phase 0).
Windows host, but the shell is git-bash: use POSIX/bash syntax with forward slashes (mkdir -p, &&, /c/...). Don't default to PowerShell.

Read the full file on GitHub · 69 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.

2mo ago First seen · 69 lines · 892 tokens per session scan A a4d9ca78c9a6

Subscribe to this mod's changes

recallchecker CLAUDE.md is an instructions file published in the GitHub repository ollo12-prog/recallchecker (0 stars, last pushed 5mo ago), licensed MIT. It adds 892 tokens to every session, about $0.0036 per session on Opus 5.5. 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.

recallchecker CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
recallchecker CLAUDE.mdollo12-prog/recallchecker	Instructions file	0	5mo ago	MIT	A	892	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

recallchecker: Instructions file for Claude Code