convergo AGENTS.md

Repository instructions for convergo, a coding-agent plugin and marketplace package. They explain the project's layout, setup commands, validation, tests, and the files that define its skills and platform versions.

In plain words
What is it for?
Use them when working on the convergo repository, especially when changing skills, marketplace metadata, generated plugin surfaces, or validation code. The documented checks include installing dependencies, validating, and running tests.
Why use it?
They give agents a shared set of rules for making changes safely and keeping generated plugin files consistent. This reduces mistakes when maintaining several plugin formats.

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/gomilesf/convergo/agents-md
Clone the repo
git clone --depth 1 https://github.com/gomilesf/convergo

Made for: Codex, OpenCode.

Per session 784 This file is loaded in full into every session.
When invoked 784 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 $0.00784 $0.00784
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2d ago against content hash dc7d6000508b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convergo 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This repository is the root of the convergo coding-agent plugin and the marketplace metadata used to distribute it.

AGENTS.md is the canonical repo instruction file. Root CLAUDE.md and GEMINI.md exist as compatibility shims for tools that look for those filenames.

Quick Start

bun install
bun run validate
bun test

Directory Layout

skills-src/        Canonical skill sources
plugins/codex/    Codex plugin root with generated runtime skills
plugins/claude/   Claude Code plugin root with generated base skills
plugins/generic/  Generic platform plugin root with generated base skills
.claude-plugin/   Claude Code marketplace descriptor
.agents/plugins/  Codex custom marketplace descriptor
.cursor-plugin/   Cursor marketplace descriptor
.opencode/        OpenCode plugin entrypoint and install notes
.pi/              Pi extension entrypoint
src/              Validation library code
scripts/          Text-interface wrappers around library code
tests/            Metadata and skill convention tests
docs/             Productization notes and architecture docs

Repo Surfaces

Changes can affect one or more surfaces:

  • canonical skill content under skills-src/
  • generated runtime skill content under plugins/*/skills/
  • platform manifests and marketplace metadata
  • validation scripts and tests
  • public installation docs

Do not assume a change is only docs or only packaging without checking the affected surface.

Plugin Maintenance

  • Keep the repo root as the marketplace/source repository root. Do not move platform plugin roots out of plugins/.
  • Keep skills-src/ as the single source of skill content. Generate platform skill roots with bun run sync.
  • Do not create a root skills/ directory. It is a forbidden legacy plugin surface.
  • Update README.md when the skill inventory, install flow, or platform support changes.
  • Run bun run validate and bun test after changes to manifests, skills, packaging entrypoints, or validation code.
  • Run bun run plugin:validate when Claude Code is available locally.
  • Do not hand-add generated release notes. Release history should be maintained separately from feature edits.

Read the full file on GitHub · 70 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 · 70 lines · 784 tokens per session scan A dc7d6000508b

Subscribe to this mod's changes

convergo AGENTS.md is an instructions file published in the GitHub repository gomilesf/convergo (7 stars, last pushed 1mo ago), licensed MIT. It adds 784 tokens to every session, about $0.0039 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.