github.com/ArweaveTeam/arweave (link)

commit signals (108)

source signals (18)

• AGENTS.mdvia agents-md

  # Arweave agent instructions
  
  Instructions for AI agents working in this repo. Shared engineering guidance
  for humans and agents lives in [`doc/agents/`](doc/agents/). This file supplies
  agent operating rules and the essentials that should always be in context.
  Before acting on a task, read every document that matches it in the table below.
  
  **When adding shared engineering guidance, put it in `doc/agents/` and link it
  here.** Do not add guidance to a tool-specific adapter (`CLAUDE.md`,
  `.claude/skills/`, `

• .agents/skills/ar-fix-issue/SKILL.mdvia unspecified

  ---
  name: ar-fix-issue
  description: Implement and test a fix for an Arweave tracker issue. Use when the user explicitly asks to fix or resolve an issue; do not use for assessment or triage alone.
  ---
  
  # Fix an issue
  
  Read [`doc/agents/issue-fixing.md`](../../../doc/agents/issue-fixing.md) and
  follow it.
  
  Treat that document as the single source of truth. Do not duplicate its
  guidance in this skill.
  

• .agents/skills/ar-code-review/SKILL.mdvia unspecified

  ---
  name: ar-code-review
  description: Review a pull request, branch, or diff using this repository's code-review conventions. Use when asked to review code changes in Arweave. Additive to any built-in code review, not a replacement for it.
  ---
  
  # Code review
  
  Read [`doc/agents/code-review.md`](../../../doc/agents/code-review.md) and
  follow it.
  
  Treat that document as the single source of truth. Do not duplicate its
  guidance in this skill.
  

• .agents/skills/ar-security-triage-internal/SKILL.mdvia unspecified

  ---
  name: ar-security-triage-internal
  description: >-
    Verify the findings in an internal security review report against current
    master and file the validated ones as issues. Use only when the user
    explicitly invokes this skill with a report file or issue URL.
  disable-model-invocation: true
  ---
  
  # Internal security report triage
  
  Read [`doc/agents/security-triage-internal.md`][doc] and follow it.
  
  Treat that document as the single source of truth. Do not duplicate its
  guidance in this skill.
  
  [doc]: ..

• .agents/skills/ar-security-triage-external/SKILL.mdvia unspecified

  ---
  name: ar-security-triage-external
  description: >-
    Reformat, evaluate against the Arweave threat model, and post an assessment
    on an externally reported security-tracker issue. Use only when the user
    explicitly invokes this skill with an issue URL.
  disable-model-invocation: true
  ---
  
  # External security report triage
  
  Read [`doc/agents/security-triage-external.md`][doc] and follow it.
  
  Treat that document as the single source of truth. Do not duplicate its
  guidance in this skill.
  
  [doc]: ../../../d

• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .agentsdirectoryvia unspecified
• .cursordirectoryvia cursor
• .cursordirectoryvia cursor
• .cursordirectoryvia cursor
• CLAUDE.mdvia claude-code

  # Arweave Development
  
  `AGENTS.md`, imported below, is the agent entry point. Shared engineering
  guidance lives in `doc/agents/`. Do not add guidance to this file — update
  `AGENTS.md` or the relevant shared document so agents that do not read
  `CLAUDE.md` still see it.
  
  @AGENTS.md
  

• .claudedirectoryvia claude-code

ignorefile signals (0)

none