agentmods.dev

chorus companion-scripts.instructions.md

Project instructions for scripts that delegate coding tasks among several command-line AI tools. They specify how to start agents, collect their output, handle failures, check installed tools, and clean up command options.

In plain words
What is it for?
Use them when changing delegation scripts, parallel agent workflows, CLI availability checks, review commands, or task-argument handling.
Why use it?
They reduce orchestration bugs such as lost errors, unreadable output, skipped tools, or flags being passed to the wrong command.

Instructions file for GitHub Copilot

10 3mo ago A scan 366 tokens original MIT
View the source file valpere/chorus
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/valpere/chorus/companion-scripts
Clone the repo
git clone --depth 1 https://github.com/valpere/chorus

Made for: GitHub Copilot.

Per session 366 This file is loaded in full into every session.
When invoked 366 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00366 $0.00366
Opus 5 $0.00183 $0.00183
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 0c34c60caf0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chorus companion-scripts.instructions.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `spawnSync` is allowed only for preflight version checks (`--version`). All actual agent invocations must use async `spawn`.
.github/instructions/companion-scripts.instructions.md · 14 lines

What it actually says

Companion script review guidelines

  • spawn must use stdio: 'pipe' when collecting output for delimited printing. Using stdio: 'inherit' is correct only for pass-through single-agent delegation (existing run/review commands).
  • spawnSync is allowed only for preflight version checks (--version). All actual agent invocations must use async spawn.
  • Each runAgent / parallel orchestration call must handle the error event on the child process to resolve gracefully — never let an unhandled error abort sibling agent calls.
  • Role prompts prepended to tasks must be clearly labelled (e.g. You are the CORRECTNESS reviewer) so the agent understands its council role without ambiguity.
  • stripFlags must remove --background, --wait, --json, and --agent/--agent=* before passing the task string to CLIs.
  • check-all subcommand must check all five target CLIs (claude, gemini, codex, cursor, kilo) and print which ones are missing with a reference to the appropriate /setup command. OpenCode is excluded — its TUI stdout is not capturable.
  • companion.mjs is a dual-purpose module: it exports helpers (stripFlags, checkCli, filterAvailable, runAgent, printDelimited, printJSON, requireAvailable, REGISTRY) for tests, and runs the CLI dispatcher when import.meta.url === \file://${process.argv[1]}`. Tests live in plugins/chorus/scripts/tests/and run withnpm test`.
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 · 14 lines · 366 tokens per session scan A 0c34c60caf0d

Subscribe to this mod's changes

chorus companion-scripts.instructions.md is an instructions file published in the GitHub repository valpere/chorus (10 stars, last pushed 3mo ago), licensed MIT. It adds 366 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsai-toolsclaude-codecodexdeveloper-toolsgemini-cli
Related

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.

eowlsdh/TokenPilot · 1,618 tokens

Project-AMBER AGENTS.md

Instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.

JJHbrams/Project-AMBER · 400 tokens

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.

eowlsdh/TokenPilot · 91 tokens

Skills AGENTS.md

AGENTS.md instructions for AceDataCloud/Skills, covering acedatacloud agent skills, available skills, ai music & audio, ai image generation and ai video generation.

AceDataCloud/Skills · 647 tokens

Skills copilot-instructions.md

Copilot instructions for AceDataCloud/Skills, covering copilot instructions for skills, sync from docs, project structure and important.

AceDataCloud/Skills · 450 tokens

semble-hooks CLAUDE.md

Instructions for benediktkraus/semble-hooks, covering semble hooks — claude.md, was ist das, projekt-typ, tech-stack and architektur-referenz.

benediktkraus/semble-hooks · 984 tokens