re-search AGENTS.md

re-search AGENTS.md is an instructions file for Codex, OpenCode from ineersa/re-search. It costs 1,155 tokens per session, scanned A, original, MIT.

Project instructions for re-search, a Symfony UX web project that uses several tools for interactive pages and browser testing.

In plain words
What is it for?
Use them when changing JavaScript behavior, page navigation, reusable Twig components, live-updating components, or browser tests.
Why use it?
They help an agent choose the right tool for each task and follow the project's coding rules.

Instructions file for CodexOpenCode

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 instructions/ineersa/re-search/agents-md
Clone the repo
git clone --depth 1 https://github.com/ineersa/re-search

Made for: Codex, OpenCode.

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 re-search AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ineersa/re-search/agents-md.svg)](https://agentmods.dev/instructions/ineersa/re-search/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ineersa/re-search/agents-md"><img src="https://agentmods.dev/badge/instructions/ineersa/re-search/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,155 This file is loaded in full into every session.
When invoked 1,155 The same file — it is already loaded in full.
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 $0.01155 $0.01155
Opus 5 $0.00577 $0.00577
Sonnet 5 $0.00231 $0.00231
Haiku 4.5 $0.00115 $0.00115

Measured 4d ago against content hash daf58830a62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

re-search AGENTS.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 4d 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.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This project uses the Symfony UX frontend stack. Six agent skills are installed to help you work with it.

Which tool to use

  • Pure JS behavior, no server round-trip -- use the stimulus skill
  • Navigation, partial page updates -- use the turbo skill
  • Reusable static UI component -- use the twig-component skill
  • Reactive component that re-renders on user input -- use the live-component skill
  • Not sure which one fits -- use the symfony-ux skill (orchestrator / decision tree)
  • Browser automation / UI testing -- use the playwright-cli skill via Task tool with subagent_type: "playwright-cli"

Key rules

  • Always render {{ attributes }} on the root element of a LiveComponent
  • Prefer HTML syntax (<twig:Alert />) over Twig syntax ({% component 'Alert' %})
  • Use data-model="debounce(300)|field" for text inputs in LiveComponents
  • Stimulus controllers must clean up listeners and observers in disconnect()
  • Turbo Frame IDs must match between the page and the server response
  • Use Turbo Streams when updating multiple page sections; use Frames for a single section
  • <twig:Turbo:Stream:Append> syntax is available since Symfony UX 2.22+
  • In PHPUnit tests, always use static assertion calls (self::assert*) instead of instance calls ($this->assert*) to keep PHPStan clean.
  • MATE tools (mandatory): Logs, profiler, PHPStan, PHPUnit, and Composer MUST use the mate-tools skill and its wrapper script (.cursor/skills/mate-tools/scripts/mate-tool-call.sh). NEVER use make test, make phpstan, or direct vendor/bin commands for these.
  • Infrastructure operations (setup, up/down, console, doctrine) MUST use make targets (no direct docker compose exec for these)
  • NEVER run Composer on the host — Composer MUST run inside the Docker container only (via make composer-* or MATE composer-* tools)
  • NEVER run PHP on the host — All PHP commands (phpunit, phpstan, console, etc.) MUST run inside the container
  • For browser testing and UI verification, ALWAYS use Task tool with subagent_type: "playwright-cli"
  • NEVER compile assets in development environment; the make tailwind-watch process handles this automatically
  • DO NOT run make assets-compile during development; only do this in production builds

Read the full file on GitHub · 70 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. 4d ago First seen · 70 lines · 1,155 tokens per session scan A daf58830a62c

Subscribe to this mod's changes

re-search AGENTS.md is an instructions file published in the GitHub repository ineersa/re-search (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,155 tokens to every session, about $0.0058 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens