codealive-skills AGENTS.md

Um arquivo de instruções para agentes de programação que trabalham com o CodeAlive, uma ferramenta que pesquisa e recupera informações do código de um projeto. Ele explica a arquitetura, os scripts e o processo de publicação.

In plain words
What is it for?
Serve para orientar inspeções e alterações no repositório, usar buscas e consultas do CodeAlive e manter o skill e o plugin atualizados.
Why use it?
Evita que o agente edite arquivos sem ler as regras corretas ou confunda essa integração com um servidor MCP, um padrão para conectar ferramentas a agentes.

Instructions file for CodexOpenCode

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/codealive-ai/codealive-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/CodeAlive-AI/codealive-skills

Made for: Codex, OpenCode.

Per session 634 This file is loaded in full into every session.
When invoked 634 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 $0.00634 $0.00634
Opus 5 $0.00317 $0.00317
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00063 $0.00063

Measured 2d ago against content hash d1ad12aaff0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codealive-skills 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 2d 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codealive-skills — notes for AI coding agents

Before editing or inspecting a target path, read every applicable AGENTS.md from the repository root through the target directory. Do not load instructions from unrelated subtrees.

This repository ships two things:

  1. The codealive-context-engine Agent Skill — a SKILL.md plus a set of Python scripts (scripts/datasources.py, search.py, grep.py, fetch.py, relationships.py, chat.py).
  2. A Claude Code plugin (.claude-plugin/plugin.json) that bundles the skill with authentication hooks and the codealive-context-explorer subagent.

What the skill is NOT

The skill is not an MCP wrapper and does not expose MCP tools. It is a set of Python scripts that call the CodeAlive REST API directly over HTTPS, using an API key resolved from the OS credential store or the CODEALIVE_API_KEY env var.

The codealive-mcp server is a separate product that exposes CodeAlive as MCP tools (get_data_sources, semantic_search, grep_search, fetch_artifacts, get_artifact_relationships). The skill and the MCP server are parallel integration paths — either works on its own, and both can be installed alongside each other.

Do not conflate them when writing or reviewing skill descriptions, docs, or commit messages.

Architecture in one sentence

SKILL.md is workflow/trigger metadata; the scripts under skills/codealive-context-engine/scripts/ are the implementation; the CodeAlive REST API is the backend. MCP is an optional sibling, not a dependency.

Releasing

  1. Edit SKILL.md, scripts, or plugin assets.
  2. Bump .claude-plugin/plugin.json version.
  3. Commit, then annotate a tag matching vX.Y.Z.
  4. Push main and the tag. CI (.github/workflows/ci.yml) runs pytest tests -v on push.
  5. Users pick up the new version via claude plugin update codealive@codealive-marketplace or npx skills update.

Writing the skill description

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 634 tokens per session scan A d1ad12aaff0e

Subscribe to this mod's changes

codealive-skills AGENTS.md is an instructions file published in the GitHub repository CodeAlive-AI/codealive-skills (14 stars, last pushed 27d ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.