git-top: Instructions file for Codex

AGENTS.md

git-top AGENTS.md is an instructions file for Codex, OpenCode from haocn-ops/git-top. It costs 1,076 tokens per session, scanned A, original, MIT.

A coding guide for Git.Top, a Cloudflare Worker application that serves web pages, APIs, agent tools, GitHub data, and database-backed features. It identifies the main source files, product flow, editing rules, and validation levels.

In plain words
What is it for?
Use it when modifying Git.Top, locating the right implementation files, understanding how GitHub data reaches the application, or checking changes.
Why use it?
It gives a coding agent the project structure and safety rules it needs before changing the repository.

Instructions file for CodexOpenCode

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

This is haocn-ops/git-top's own configuration. It tells Codex and OpenCode how to work on git-top 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 git-top configures →

Reuse

Borrowing it

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

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 git-top AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/haocn-ops/git-top/agents-md"><img src="https://agentmods.dev/badge/instructions/haocn-ops/git-top/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,076 This file is loaded in full into every session.
When invoked 1,076 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 $0.01076 $0.01076
Opus 5.5 $0.00430 $0.00430
Sonnet 5.5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured 2mo ago against content hash 7aabec2b8b3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-top 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 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.

AGENTS.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git.Top Coding Agent Guide

This guide is the shortest safe entry point for coding agents that need to modify Git.Top.

Product Shape

Git.Top is a Cloudflare Worker knowledge product. The Worker is the only runtime surface: it serves human HTML pages, REST APIs, MCP tools, GRP, GitHub sync, governance jobs, D1-backed data, OpenAPI, and LLM discovery files.

Core flow:

GitHub API
  -> sync and derived data
  -> Cloudflare D1
  -> Worker pages, REST APIs, MCP tools, GRP, trust, quality, and eval gates

Key Files

  • src/index.ts: Worker routing for pages, API, MCP, static discovery files, scheduled tasks, and admin routes.
  • src/api.ts: REST API handlers and request parsing.
  • src/mcp.ts: MCP discovery, tool schemas, and tool calls.
  • src/openapi.ts: OpenAPI document exposed as /openapi.json and /api/openapi.json.
  • src/agent-map.ts: machine-readable map from concepts to pages, REST endpoints, MCP tools, output fields, and trust fields.
  • src/project-search.ts: search, recommendation, project lookup, alternatives, and related project helpers.
  • src/quality.ts, src/trust-gate.ts, src/sync-status.ts: trust, quality, and freshness surfaces.
  • src/db.ts, src/db-*-store.ts, src/db-mapping.ts: D1 schema access and mapping.
  • data/seed-repositories.json: curated source corpus.
  • scripts/*.mjs: validation, eval, seeding, smoke, governance, and release automation.
  • docs/API.md, docs/MCP.md, docs/AGENT_QUICKSTART.md: primary agent integration docs.
  • docs/AGENT_NATIVE_ASSESSMENT_AND_OPTIMIZATION_PLAN.md: current agent-native product assessment and roadmap.
  • docs/AGENT_NATIVE_OPTIMIZATION_IMPLEMENTATION_REPORT.md: completed implementation record for the agent-native optimization pass.
  • docs/AGENT_NATIVE_OPTIMIZATION_PR_SUMMARY.md: review-ready summary of the optimization changes.

Edit Rules

  • Keep the Worker as the source of truth. Do not add a separate app runtime unless the product direction explicitly changes.
  • Preserve metadata.source, metadata.reason, require_d1, and trust fields on agent-facing responses.
  • Prefer adding structured fields over prose-only changes when agents need to consume a result.
  • Keep exact-intent search behavior distinct from broad ranking=browse discovery.
  • Do not silently change generated artifacts. If changing source data or eval fixtures, regenerate and validate the derived files.
  • Treat existing uncommitted changes as user work. Read before editing and avoid unrelated rewrites.

Read the full file on GitHub · 131 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. 2mo ago First seen · 131 lines · 1,076 tokens per session scan A 7aabec2b8b3d

Subscribe to this mod's changes

git-top AGENTS.md is an instructions file published in the GitHub repository haocn-ops/git-top (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,076 tokens to every session, about $0.0043 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.

Related

git-top AGENTS.md compared with instructions from other repositories

git-top AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-top AGENTS.mdhaocn-ops/git-topInstructions file01mo agoMITA1,076Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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