agent-skills AGENTS.md

agent-skills AGENTS.md is an instructions file for Codex, OpenCode from zephexMCP/agent-skills. It costs 488 tokens per session, scanned C, original, MIT.

A set of instructions for Zephex, a tool service that helps an agent understand and work with a codebase. It includes project context, code search, architecture explanations, package checks, tests, security checks, and project memory.

In plain words
What is it for?
Use it when starting work in a new repository, locating code for a feature or fix, understanding architecture, checking packages for risks, running tests, auditing website security headers, or saving project facts.
Why use it?
It gives the agent a defined way to inspect an unfamiliar repository, trace how its parts connect, check dependencies, and verify changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

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/zephexmcp/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/zephexMCP/agent-skills

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 agent-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zephexmcp/agent-skills/agents-md.svg)](https://agentmods.dev/instructions/zephexmcp/agent-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zephexmcp/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zephexmcp/agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 488 This file is loaded in full into every session.
When invoked 488 The same file — it is already loaded in full.
Security scan C 2 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 5.1 $0.00488 $0.00488
Opus 5 $0.00244 $0.00244
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 5d ago against content hash cff4bb3da1b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

agent-skills AGENTS.md scanned grade C with 2 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

Full routing: `skills/zephex/SKILL.md`. Connect: `npx zephex setup`. CLI install: `curl -fsSL https://zephex.dev/cli/install.sh | bash`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Full routing: `skills/zephex/SKILL.md`. Connect: `npx zephex setup`. CLI install: `curl -fsSL https://zephex.dev/cli/install.sh | bash`.
AGENTS.md · 38 lines

What it actually says

Zephex

Auto-loaded session gate for Claude Code, Gemini CLI, OpenCode, Codex, and similar agents.

Zephex MCP at https://zephex.dev/mcpten tools for the user's codebase (not training data).

Tools

Tool One line
get_project_context Stack, scripts, auth, monorepo (topic slices)
find_code BM25 + ripgrep search
read_code AST symbol / file / outline
explain_architecture Wiring map (entry, auth, integrations)
check_package Registry safety + upgrade/CVE tasks
check_test Test Pulse — run suite + failure health
audit_headers Live HTTPS URL security audit
project_memory Remember / recall project facts
keep_thinking Multi-step reasoning with loop detection
Zephex_dev_info Expert playbooks (not their private repo)

Workflow

Situation Chain
New repo get_project_context (topic identity / run) → optional explain_architecture
Feature / fix find_coderead_codecheck_test after edits
How it wires explain_architecture
Before install check_package (task=check, then upgrade / security if needed)
Live URL audit_headers
Remember facts project_memory
Stuck keep_thinking with lastActions
Terminal / free layout CLI: zephex deep --json · structure --agent · overview · test / check test failures

Pass absolute path (or github:owner/repo) on every repo tool. Prefer MCP when connected. Call check_package before install suggestions. If they named Zephex, call a tool (or CLI command) before answering about their code.

Full routing: skills/zephex/SKILL.md. Connect: npx zephex setup. CLI install: curl -fsSL https://zephex.dev/cli/install.sh | bash.

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. 5d ago First seen · 38 lines · 488 tokens per session scan C cff4bb3da1b5

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository zephexMCP/agent-skills (5 stars, last pushed 23d ago), licensed MIT. It adds 488 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.