file-prompts

file-prompts is a skill for Claude Code from ils15/pantheon-legacy. It costs 21 tokens per session (814 once invoked), scanned A, original, MIT.

A way to keep coding-agent prompts in separate files instead of embedding them in configuration. The files can be versioned, shared, and referenced by path.

In plain words
What is it for?
Use it to store separate prompts for different agents and load them from project-relative, home-relative, or absolute paths.
Why use it?
It makes long prompts easier to maintain and keeps configuration files smaller and clearer.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: mentions OpenCode.

Good fit Use it to store separate prompts for different agents and load them from project-relative, home-relative, or absolute paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ils15/pantheon-legacy/file-prompts
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.

Any agent
npx skills add ils15/pantheon-legacy --skill file-prompts
Clone the repo
git clone --depth 1 https://github.com/ils15/pantheon-legacy

Made for: Claude Code.

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 file-prompts

README.md
[![agentmods](https://agentmods.dev/badge/skills/ils15/pantheon-legacy/file-prompts/github.svg)](https://agentmods.dev/skills/ils15/pantheon-legacy/file-prompts)
Your own site
<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/file-prompts"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/file-prompts/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 file-prompts

Your own site · 80×15
<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/file-prompts"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/file-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00021 $0.00814
Opus 5 $0.00010 $0.00407
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00081

Measured 8d ago against content hash e13122b19da2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

file-prompts 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 8d 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.

skills/file-prompts/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File-Based Prompts — External Prompt Loading

Use this skill to load agent system prompts from external files instead of embedding them in config. Enables version control, sharing, and cleaner configuration.


How It Works

Instead of embedding prompts in JSON:

// ❌ Embedded prompt (hard to version, hard to share)
{
  "agents": {
    "hermes": {
      "prompt": "You are Hermes, the backend specialist. Your expertise is..."
    }
  }
}

Load from files:

// ✅ File-based prompt (versioned, shareable)
{
  "agents": {
    "hermes": {
      "prompt": "file://./prompts/hermes-prompt.md"
    }
  }
}

Supported Path Formats

Format Example Resolves To
Relative file://./prompts/hermes.md <project>/prompts/hermes.md
Home expansion file://~/prompts/hermes.md ~/.config/opencode/prompts/hermes.md
Absolute file:///opt/prompts/hermes.md /opt/prompts/hermes.md

Use Cases

1. Version Control Prompts Separately

project/
├── opencode.json          # Config (prompt references)
├── prompts/
│   ├── hermes-prompt.md   # Backend specialist prompt
│   ├── aphrodite-prompt.md # Frontend specialist prompt
│   └── themis-prompt.md   # Review specialist prompt

Prompts can be versioned independently from config.

2. Share Prompts Across Projects

~/.config/opencode/prompts/
├── hermes-prompt.md       # Shared across all projects
├── aphrodite-prompt.md
└── themis-prompt.md
{
  "agents": {
    "hermes": {
      "prompt": "file://~/prompts/hermes-prompt.md"
    }
  }
}

3. Append Category-Specific Context

{
  "categories": {
    "deep": {
      "prompt_append": "file://./prompts/deep-category-append.md"
    }
  }
}

Appends additional context to the category's prompt without duplicating the base prompt.


Prompt File Format

Prompt files are plain markdown:

# Hermes — Backend Specialist

You are the **BACKEND TASK IMPLEMENTER** (Hermes) called by Zeus to implement
FastAPI endpoints, services, and routers.

## Core Principles
- TDD first: write tests that fail, write minimal code to pass
- Async/await on all I/O operations
- Type hints on all parameters
- Max 300 lines per file

## Your Tools
- FastAPI, SQLAlchemy, Pydantic, Redis
- pytest for testing
- ruff for linting

## When to Delegate
- @apollo for codebase discovery
- @themis for code review
- @demeter for database migrations

Read the full file on GitHub · 149 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. 8d ago First seen · 149 lines · 21 tokens per session scan A e13122b19da2

Subscribe to this mod's changes

file-prompts is a skill published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 814 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens