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.
npx agentmods add instructions/valpere/chorus/agents-mdgit clone --depth 1 https://github.com/valpere/chorusWrote 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.
[](https://agentmods.dev/instructions/valpere/chorus/agents-md)<a href="https://agentmods.dev/instructions/valpere/chorus/agents-md"><img src="https://agentmods.dev/badge/instructions/valpere/chorus/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01163 | $0.01163 |
| Opus 5 | $0.00581 | $0.00581 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
chorus 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chorus — Agent Context
Cross-agent plugin collection connecting six AI coding CLIs in a full 6×6 delegation mesh.
What this project is
Every agent can delegate to every other agent. The project ships plugins/skills/rules for each host so they can invoke the others without leaving their own interface.
Agents: Claude Code, OpenCode, Gemini CLI, Codex, Cursor Agent CLI, Kilo Code CLI
OpenCode is excluded from parallel workflow patterns — its TUI stdout is not capturable.
Project structure
chorus/
├── plugins/ # Claude Code plugins (one per target agent)
│ ├── claude/ # Self-delegation (second Claude instance)
│ ├── opencode/
│ ├── gemini/
│ ├── codex/
│ ├── cursor/
│ ├── kilo/
│ └── chorus/ # Workflow patterns (orchestrate multiple agents)
│ ├── commands/ # council.md, review.md, debug.md, second-opinion.md, vote.md
│ └── scripts/companion.mjs # Parallel orchestrator: spawns agents, captures output
├── for-gemini/ # Gemini CLI skills (SKILL.md per target)
├── for-codex/ # Codex skills (SKILL.md per target)
├── for-cursor/ # Cursor Agent CLI rules (RULE.mdc per target)
├── for-kilo/ # Kilo Code CLI skills (SKILL.md per target)
└── for-opencode/ # OpenCode MCP npm package
└── src/index.js # MCP stdio server exposing delegate_* tools
Each for-*/ directory has 10 entries: 5 delegation targets + council + parallel-review + parallel-debug + second-opinion + vote.
Key files
| File | Purpose |
|---|---|
plugins/chorus/scripts/companion.mjs |
Core orchestrator. Runs council, review, debug, second-opinion, vote subcommands. Exports helpers for tests. council/review/debug/vote require ≥2 agents; second-opinion requires ≥1. |
plugins/chorus/scripts/tests/ |
node --test smoke tests for companion.mjs helpers and subcommands (29 tests). |
for-opencode/src/tests/ |
node --test hermetic MCP server tests — tools/list, check_agents, council, second_opinion, vote (8 tests). |
plugins/chorus/commands/*.md |
Claude Code slash-command specs for each workflow pattern. |
for-opencode/src/index.js |
MCP server. Exports delegate_* tools, check_agents, council (strict mode), parallel_review, parallel_debug, second_opinion (with fallback), vote. |
.claude-plugin/marketplace.json |
Claude Code plugin registry. |
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.
- 3d ago First seen · 93 lines · 1,163 tokens per session scan A 8522d01a3451
chorus AGENTS.md is an instructions file published in the GitHub repository valpere/chorus (10 stars, last pushed 3mo ago), licensed MIT. It adds 1,163 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
TokenPilot AGENTS.md
AGENTS.md instructions for eowlsdh/TokenPilot, covering project knowledge base, structure, where to look, code map and conventions.
Project-AMBER AGENTS.md
Instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.
TokenPilot CLAUDE.md
Claude Code instructions for eowlsdh/TokenPilot, a project described as: Local-first macOS menu bar utility for AI coding-tool usage metadata.
semble-hooks CLAUDE.md
Instructions for benediktkraus/semble-hooks, covering semble hooks — claude.md, was ist das, projekt-typ, tech-stack and architektur-referenz.
ystack GEMINI.md
Gemini CLI instructions for Yasuui/ystack, covering gemini.md — ystack ⚡, this is the primary config file for antigravity ide, agents.md remains for compatibility with other tools, identity and subagent dispatch.
Project-AMBER project-guides.instructions.md
Project coding guidelines, todo monitoring rules, and context for AI agents working on Project Engram.