reshapr: Instructions file for Codex

AGENTS.md

reshapr AGENTS.md is an instructions file for Codex, OpenCode from reshaprio/reshapr. It costs 2,307 tokens per session, scanned A, original, Apache-2.0.

A repository instruction document describing reShapr's architecture, development commands, and build requirements. It explains how its control service, gateway, command-line tool, and web interface fit together.

In plain words
What is it for?
Use it to understand the repository layout, service boundaries, local development process, and full Maven build requirements for reShapr.
Why use it?
It gives coding agents and developers a common set of project rules before they edit or build the code. This reduces mistakes caused by using the wrong service, command, framework assumption, or Java setup.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is reshaprio/reshapr's own configuration. It tells Codex and OpenCode how to work on reshapr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reshapr configures →

Reuse

Borrowing it

Nothing to install: this file belongs to reshaprio/reshapr. 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/reshaprio/reshapr/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/reshaprio/reshapr

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 reshapr AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reshaprio/reshapr/agents-md/github.svg)](https://agentmods.dev/instructions/reshaprio/reshapr/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/reshaprio/reshapr/agents-md"><img src="https://agentmods.dev/badge/instructions/reshaprio/reshapr/agents-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.

agentmods 80×15 button for reshapr AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/reshaprio/reshapr/agents-md"><img src="https://agentmods.dev/badge/instructions/reshaprio/reshapr/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,307 This file is loaded in full into every session.
When invoked 2,307 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02307 $0.02307
Opus 5.5 $0.00923 $0.00923
Sonnet 5.5 $0.00461 $0.00461
Haiku 4.5 $0.00231 $0.00231

Measured 17d ago against content hash dbf228540ba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reshapr 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 17d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

reShapr is the open source runtime that turns existing REST/GraphQL/gRPC APIs AI-Native, without rebuilding them, by transforming them into governed, LLM-friendly MCP (Model Context Protocol) tools. It solves "Context Overload" by filtering and slimming API payloads before they reach LLMs.

Architecture

Three core runtime services communicate via gRPC, plus a web UI and a CLI:

                             ┌─────────────────────────────────────┐
                             │         reShapr Platform            │
                             │                                     │
  ┌──────────┐  MCP/HTTP     │  ┌──────────────────────────────┐   │
  │  AI Agent│──────────────>│  │      Gateway (proxy)         │   │──> REST / GraphQL / gRPC
  │  or LLM  │               │  │      :7777                   │   │    Backend APIs
  └──────────┘               │  └──────────┬───────────────────┘   │
                             │             │ gRPC (EDS + GHS)      │
  ┌──────────┐  REST API     │  ┌──────────▼───────────────────┐   │
  │  CLI /   │──────────────>│  │    Control Plane (ctrl)      │───┼──> PostgreSQL
  │  Web UI  │               │  │    :5555                     │   │
  └──────────┘               │  └──────────────────────────────┘   │
                             └─────────────────────────────────────┘

Each component in more detail:

  • Control Plane (control-plane/) — Quarkus service on port 5555. Manages services, expositions, organizations, users, gateways. Uses PostgreSQL + Flyway migrations + Hibernate ORM Panache with multi-tenant DISCRIMINATOR strategy. Hazelcast for caching.
  • Proxy/Gateway (proxy/) — Quarkus service on port 7777. Receives MCP requests, discovers expositions via gRPC from the control plane (eds-v1.proto, ghs-v1.proto), proxies calls to backend APIs. Supports REST, GraphQL, gRPC backends.
    • Clustering: multiple gateway instances form an Infinispan cluster via JGroups DNS_PING, replicating session, elicitation, and secret-resolution state so any gateway can handle any request. Controlled by the reshapr.infinispan.stack JVM property (reshapr-local for a single node, reshapr-k8s for a clustered setup).
    • Caching: doesn't round-trip to the control plane on every request. A GatewayRegistry holds raw exposition metadata and artifact content, populated at startup and refreshed on every change event. A WorkCache (Caffeine LRU) holds the parsed form of those artifacts, for example a parsed OpenAPI document, so re-parsing is avoided across calls.
  • CLI (cli/) — TypeScript/Node.js CLI (@reshapr/reshapr-cli) built with Commander.js. Manages login, import, service lifecycle, and local Docker-based platform via reshapr run.
  • Web UI (web-ui/) — SvelteKit 5 app (@reshapr/reshapr-web-ui, Svelte 5 runes + TailwindCSS 4 + bits-ui) deployed with adapter-node (SSR). Standalone, not a Maven module. Talks to the control-plane admin API server-side via RESHAPR_ADMIN_API_KEY (see web-ui/src/lib/server/proxy.ts, auth.ts). Runs on 5173 in dev (Vite), 3333 in the container.

Read the full file on GitHub · 144 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. 17d ago Changed · +14 tokens per session dbf228540ba5
  2. 18d ago Changed · -11 tokens per session 869924aa1a62
  3. 1mo ago Changed · -24 lines · -204 tokens per session 201d4a14f70b
  4. 1mo ago Changed · +68 lines · +1,113 tokens per session 3d3def0c5d4f
  5. 1mo ago First seen · 100 lines · 1,395 tokens per session scan A 43d21a4d7242

Subscribe to this mod's changes

reshapr AGENTS.md is an instructions file published in the GitHub repository reshaprio/reshapr (172 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,307 tokens to every session, about $0.0092 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 2026-09-24.

Related

reshapr AGENTS.md compared with instructions from other repositories

reshapr AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
reshapr AGENTS.mdreshaprio/reshaprInstructions file172yesterdayApache-2.0A2,307Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode