agentmods.dev

skillport AGENTS.md

skillport AGENTS.md is an instructions file for Codex, OpenCode from eikonoikari1/skillport. It costs 586 tokens per session, scanned A, original, MIT.

A set of coding instructions for the Skillport project, which converts skills and rules between AI coding tools such as Claude Code, Cursor, Codex CLI, and Copilot.

In plain words
What is it for?
Use it when modifying parsers, emitters, adapters, detection, or command-line conversion behavior.
Why use it?
It explains the project's shared intermediate format and conversion architecture, helping changes fit its design.

Instructions file for CodexOpenCode

not rated 1 5mo ago A scan 586 tokens original MIT
View the source file eikonoikari1/skillport
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/eikonoikari1/skillport/agents-md
Clone the repo
git clone --depth 1 https://github.com/eikonoikari1/skillport

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 skillport AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eikonoikari1/skillport/agents-md.svg)](https://agentmods.dev/instructions/eikonoikari1/skillport/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/eikonoikari1/skillport/agents-md"><img src="https://agentmods.dev/badge/instructions/eikonoikari1/skillport/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 586 This file is loaded in full into every session.
When invoked 586 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 $0.00586 $0.00586
Opus 5 $0.00293 $0.00293
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00059 $0.00059

Measured 5d ago against content hash 553c0a8dfbf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillport 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 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.

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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skillport

Universal skill/rule adapter for AI coding harnesses.

What this project is

skillport converts skills, rules, and instructions between Claude Code, Cursor, Codex CLI, OpenClaw, GitHub Copilot, and Windsurf. The primary source lives in claude-code/. Pre-ported versions for other harnesses are in their respective directories.

Architecture

  • IR-based: Every conversion goes through an intermediate representation (src/ir.ts). No N-to-N format converters.
  • Parse → IR → Emit: Parsers in src/parsers/ read native formats. Emitters in src/emitters/ write them. Adapters in src/adapters/ handle cross-harness feature mapping.
  • Three strategies for non-portable features: native mapping, functional shims (wrapper scripts, instruction text), or annotated comments. Nothing is silently dropped.

Key files

  • claude-code/SKILL.md -- the skill definition (conversational-first, parses user intent for WHAT/FROM/TO)
  • claude-code/bin/skillport.ts -- CLI entry point (commander-based, convert and detect subcommands)
  • claude-code/src/ir.ts -- SkillIR type definitions, parity scoring
  • claude-code/src/detect.ts -- auto-detection of harness format from file paths and frontmatter
  • claude-code/src/utils/warnings.ts -- parity report formatting

Conventions

  • Parsers return SkillIR. Emitters accept SkillIR and return ConversionResult (files + warnings + parity).
  • Every emitter must populate warnings and features arrays for the parity report.
  • Use buildParity() from utils/warnings.ts to compute the final assessment.
  • Shims go in scripts/ within the emitted skill directory. Annotations go as HTML comments in the body.

Adding a new harness

  1. Add the harness name to HarnessTypes in src/ir.ts
  2. Create src/parsers/<harness>.ts with a parse function returning SkillIR
  3. Create src/emitters/<harness>.ts with an emit function returning ConversionResult
  4. Add entries to the adapter mapping tables in src/adapters/
  5. Wire the parser and emitter into bin/skillport.ts (the parseSource and emitTarget functions)
  6. Update the detection logic in src/detect.ts

Read the full file on GitHub · 46 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. 5d ago First seen · 46 lines · 586 tokens per session scan A 553c0a8dfbf6

Subscribe to this mod's changes

skillport AGENTS.md is an instructions file published in the GitHub repository eikonoikari1/skillport (1 stars, last pushed 5mo ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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.

Building agentsagent-skillsai-codingclaude-codecodexcopilotcursor
Related

Other instructions, from other repositories

memorix CLAUDE.md

Claude Code instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.

AVIDS2/memorix · 1,073 tokens

memorix GEMINI.md

Gemini CLI instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.

AVIDS2/memorix · 846 tokens

Ctxo CLAUDE.md

Claude Code instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).

alperhankendi/Ctxo · 5,885 tokens

draft CLAUDE.md

Claude Code instructions for drafthq/draft, covering claude.md, repository overview, build & test commands, run a single test and etc. — any test in tests/ is independently executable.

drafthq/draft · 3,260 tokens

Ctxo copilot-instructions.md

Copilot instructions for alperhankendi/Ctxo, covering ctxo mcp tool usage (mandatory), before any code modification, before starting a task, before reviewing a pr or diff and when exploring or searching code.

alperhankendi/Ctxo · 408 tokens

specops CLAUDE.md

Instructions for sanmak/specops, covering claude.md, what is specops, build & validate commands, run all tests (single command) and generate for a single platform.

sanmak/specops · 1,576 tokens