remorafish AGENTS.md

A set of repository instructions for RemoraFish, a framework that connects AI applications to online services through provider adapters and an MCP interface. It describes the framework's architecture, ownership boundaries, and credential-safety rules.

In plain words
What is it for?
Use it when adding or changing a service provider, handling credentials, working on chat routing, or checking the control and data flows in RemoraFish.
Why use it?
It helps developers keep provider-specific code separate from shared chat routing and session management. It also points them to the documents that define the framework's contracts and operating 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/howdeploy/remorafish/agents-md
Clone the repo
git clone --depth 1 https://github.com/howdeploy/remorafish

Made for: Codex, OpenCode.

Per session 795 This file is loaded in full into every session.
When invoked 795 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 $0.00795 $0.00795
Opus 5 $0.00398 $0.00398
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00080 $0.00080

Measured 2d ago against content hash 50e64396b821, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remorafish 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 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.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RemoraFish agent guide

This repository is an agent-first Web2API and MCP framework. Treat the Python framework and its tests as the product; remorafish/webui/ is a bundled reference client that demonstrates the public control and data planes.

Read first

  1. README.md for the three supported use cases.
  2. docs/architecture.md for boundaries and runtime flow.
  3. docs/framework.md before adding or changing a provider.
  4. docs/agent-control-plane.md before operating local accounts.

Current source and tests are authoritative when historical DESIGN.md or RESEARCH.md material differs from executable behavior.

Architecture invariants

  • Provider authors import the stable contract from remorafish.framework.
  • A provider owns its manifest, credential mapping, health probe, endpoints, model catalog, and conversion of its upstream stream into neutral events.
  • ChatEngine owns routing, account affinity, failover, conversations, and transport session lifecycle. Do not duplicate those policies in adapters.
  • OpenAI, Anthropic, inference MCP, CLI, and the reference UI are surfaces over the same runtime; they must not implement provider protocols independently.
  • External providers use the remorafish.providers Python entry-point group.
  • The regular remorafish mcp server is inference-only. Account operations belong exclusively to the capability-gated remorafish admin-mcp server.

Credential safety invariants

  • Operate only accounts and browser profiles owned by the user or explicitly authorized for that user.
  • Never print, log, serialize into an agent response, or place in a prompt a raw token, cookie, password, authenticated proxy URL, or vault key.
  • Browser scans require explicit confirmation. They return opaque scan IDs and masked candidates; raw values remain in the local CredentialBroker for at most ten minutes.
  • Import, login, enable, and removal operations require the corresponding Admin MCP server capability. Destructive removal also requires the exact account ID a second time.
  • Keep account control local. Do not expose Admin MCP over the public HTTP data plane.
  • Do not perform live-account or browser smoke tests unless the user explicitly authorizes them for the current task.

Read the full file on GitHub · 90 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 · 90 lines · 795 tokens per session scan A 50e64396b821

Subscribe to this mod's changes

remorafish AGENTS.md is an instructions file published in the GitHub repository howdeploy/remorafish (4 stars, last pushed 11d ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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