agentmods.dev

arcforge AGENTS.md

Repository instructions for Arcforge, a portable collection of skills for AI coding agents. They define rules for maintaining skills, documenting behavior, reviewing changes, and verifying the repository.

In plain words
What is it for?
Use them when adding or changing an Arcforge skill. They cover reading linked guidance, keeping skill files portable and within size limits, preserving required sections, and running the repository review process.
Why use it?
They reduce inconsistent skill behavior by requiring shared formats, project-specific guidance, tests or behavioral cases, and review checks before changes are considered complete.

Instructions file for CodexOpenCode

16 6d ago A scan 1,251 tokens original MIT
View the source file d4rkNinja/arcforge
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/d4rkninja/arcforge/agents-md
Clone the repo
git clone --depth 1 https://github.com/d4rkNinja/arcforge

Made for: Codex, OpenCode.

Per session 1,251 This file is loaded in full into every session.
When invoked 1,251 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 $0.01251 $0.01251
Opus 5 $0.00626 $0.00626
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 3d ago against content hash b24c521fbdd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arcforge 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Instructions for Coding Agents

Purpose

This repository publishes portable Agent Skills for production system architecture. Core behavior belongs in the portable skill format and must remain usable across compatible runtimes.

Portable skills live under skills/*/. Each skill must remain usable by Claude Code, Codex, and other Agent Skills-compatible runtimes without depending on a vendor-specific control plane.

Required workflow

  1. Read the affected SKILL.md and its linked references completely.
  2. Add or update a runtime-neutral behavioral case before changing observable behavior, then review it with an approved target model.
  3. Keep skill frontmatter valid and make the directory name equal to the frontmatter name.
  4. Keep each primary SKILL.md at 500 lines or fewer; move deep material into references/, reusable forms into assets/, and worked calibration artifacts into examples/.
  5. Preserve the exact headings ## Output Contract and ## Stop Conditions in each primary skill.
  6. Run portable skill discovery and perform the repository review checklist before claiming completion.
  7. Read full output and report any unrun agent-specific or behavioral verification honestly.

Portable skill rules

  • Use only the shared Agent Skills frontmatter fields unless a runtime-specific field is clearly optional and isolated.
  • Keep portable SKILL.md frontmatter to name and description; place Codex UI metadata in the optional agents/openai.yaml file.
  • Keep installation and activation compatible with the shared Agent Skills format across supported runtimes.
  • Keep descriptions specific enough for implicit activation and include concrete trigger words.
  • Reference supporting files with paths relative to the skill directory.
  • Keep skill behavior in natural-language instructions, references, examples, and reusable Markdown assets.
  • Protect secrets, tokens, personal data, and runtime state from repository content.

Architecture content rules

Read the full file on GitHub · 88 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 · 88 lines · 1,251 tokens per session scan A b24c521fbdd0

Subscribe to this mod's changes

arcforge AGENTS.md is an instructions file published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed 6d ago), licensed MIT. It adds 1,251 tokens to every session, about $0.0063 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 2026-08-30.

agent-skillsarchitectureclaude-code
Related

Other instructions, from other repositories

cli CLAUDE.md

Instructions for archcore-ai/cli, covering claude.md, search priority, archcore operations, managed blocks and build and test commands.

archcore-ai/cli · 1,528 tokens

mcp-adr-analysis-server copilot-instructions.md

Instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.

tosin2013/mcp-adr-analysis-server · 2,839 tokens

sruja AGENTS.md

Instructions for sruja-ai/sruja, covering ⚡ quick reference (top 5 commands), architecture setup (ai agent workflow), step 1: understand the codebase, step 2: classify the architecture and step 3: generate ide context.

sruja-ai/sruja · 6,175 tokens

oh-my-mermaid CLAUDE.md

Instructions for oh-my-mermaid/oh-my-mermaid, covering project rules, readme localization, versioning, commits and terminology.

oh-my-mermaid/oh-my-mermaid · 311 tokens

neat CLAUDE.md

Instructions for neat-technologies/neat, covering claude.md, binding rules, what neat is, what success looks like and conventions.

neat-technologies/neat · 909 tokens

agentic AGENTS.md

Instructions for soulcodex/agentic, covering agentic library — agent instructions, what this repo contains, rules for working in this repo, file authoring and skill authoring.

soulcodex/agentic · 1,585 tokens