gemini-web-wrapper AGENTS.md

Repository instructions for a Gemini web wrapper project, including its code layout, instruction priority, and working rules. A repository is the folder containing a project's source code and configuration.

In plain words
What is it for?
Guide work on the React web app, FastAPI backend, shared settings, language-model providers, repository guidance files, and related project structure.
Why use it?
They give coding agents a shared reference for where parts of the application belong and which instructions take precedence. This reduces conflicting changes across the project.

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/ven0m0/gemini-web-wrapper/agents-md
Clone the repo
git clone --depth 1 https://github.com/Ven0m0/gemini-web-wrapper

Made for: Codex, OpenCode.

Per session 1,120 This file is loaded in full into every session.
When invoked 1,120 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 $0.01120 $0.01120
Opus 5 $0.00560 $0.00560
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 3d ago against content hash b6878615cf8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini-web-wrapper 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 3d 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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Gemini Web Wrapper

Canonical repository guidance for Copilot, OpenCode, and other agents. Keep this file as the long-form source of truth, keep .github/copilot-instructions.md short and aligned with it, and keep CLAUDE.md as a symlink to this file.

Instruction precedence

  1. AGENTS.md for repo-wide rules and workflows.
  2. .github/instructions/*.instructions.md for path-specific guidance.
  3. .github/skills/*/SKILL.md for reusable task workflows invoked on demand.

Repository map

  • apps/web — React 19 + TypeScript + Vite 8 PWA
    • Shared state lives in apps/web/src/store.ts.
    • API clients and non-trivial browser logic belong in apps/web/src/services/.
    • Tooling comes from apps/web/package.json and the root Bun workspace.
  • apps/api — FastAPI backend
    • App entrypoint: apps/api/src/affine/api/server.py
    • Module entrypoint: apps/api/src/affine/api/__main__.py
    • Main routes include /health, /v1/models, /v1/chat/completions, /v1/agent/chat, /v1/repo/*, and /v1/local-index/*.
  • packages/config — typed settings and cached get_settings()
  • packages/llm-core — provider interfaces, factory, and built-in providers
  • packages/shared/python — shared schemas and OpenAI-style request/response models
  • packages/code-index — repository discovery, parsing, chunking, embedding, and search helpers under packages/code-index/src/affine/code_index/

Source of truth

When guidance disagrees, prefer:

  1. Current code in apps/ and packages/
  2. .github/workflows/ci.yml
  3. README.md
  4. Other docs under docs/

Use the code and CI as the baseline, and update guidance when runtime behavior or validation changes.

Working rules

  • Keep changes focused, local, and easy to review.
  • Use the repository toolchains only: bun for JS/TS and uv for Python.
  • Follow the existing layout instead of introducing parallel patterns.
  • Keep repo-wide guidance here and keep path-specific details in .github/instructions/.
  • Update related guidance files together when commands, entrypoints, or workflows change.

Read the full file on GitHub · 118 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. 3d ago First seen · 118 lines · 1,120 tokens per session scan A b6878615cf8c

Subscribe to this mod's changes

gemini-web-wrapper AGENTS.md is an instructions file published in the GitHub repository Ven0m0/gemini-web-wrapper (4 stars, last pushed 3d ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0056 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