Parallel Code is an interface for running multiple AI coding agents at the same time, with each agent working in its own Git worktree and branch. Developers use it to dispatch tasks to Claude Code, Codex CLI, Gemini CLI, or Copilot CLI, then review and merge their changes. The catalogue instruction supports operating these parallel agent sessions.
Borrowing it
Nothing to install: this file belongs to johannesjo/parallel-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/johannesjo/parallel-code/main/AGENTS.mdgit clone --depth 1 https://github.com/johannesjo/parallel-codeWrote 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/johannesjo/parallel-code/agents-md)<a href="https://agentmods.dev/instructions/johannesjo/parallel-code/agents-md"><img src="https://agentmods.dev/badge/instructions/johannesjo/parallel-code/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/johannesjo/parallel-code/agents-md"><img src="https://agentmods.dev/badge/instructions/johannesjo/parallel-code/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02133 | $0.02133 |
| Opus 5.5 | $0.00853 | $0.00853 |
| Sonnet 5.5 | $0.00427 | $0.00427 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
parallel-code 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Code
Electron desktop app for running coding agents in isolated Git worktrees. Desktop releases target macOS and Linux only. The phone UI is a separate web frontend.
- Frontend: SolidJS, strict TypeScript, Vite.
- Backend: Node.js, Electron, node-pty.
- Package manager: npm. CI uses Node.js 22.
- Shared project guidance lives here;
CLAUDE.mdimports this file. Keep personal model and workflow preferences in global instructions.
Development and verification
npm run devstarts the Electron development app.npm run buildbuilds and packages the app;npm run build:remoterebuilds the phone UI.npm run typecheckchecks frontend types and their imports; it does not cover the entire Electron backend.npm run typecheck:electronchecks backend TypeScript;npm run compilealso emitsdist-electron/.- Run focused tests while developing:
npm run test:unit -- path/to/file.test.tsfor logic/backend tests (Node environment).npm run test:client -- path/to/file.client.test.tsxfor DOM/component tests (happy-dom).npm run test:changedruns the tests of both suites that uncommitted changes affect; run it before committing.
- For code changes, run
npm run checkand relevant tests before handoff. It runs backend and frontend type checking, lint, and a formatting check in parallel, reports every failing step in one run, and prints output only for failures; caches innode_modules/.cachemake repeat runs fast. For documentation-only changes, check the changed files with Prettier. - Vitest switches to its compact
agentreporter (failures only) when it detects a coding agent, so don't pass--reporteror pipe test output throughtail. npm testruns both test suites.npm run test:ciadds unit coverage thresholds.npm run check:staticincludes dead-code and architecture checks as well as type checking and lint; use it when changing exports or module dependencies.- See
.github/workflows/ci.ymlfor the complete CI sequence, including security-rule fixture tests and the real-PTY coordinator test. Ordinary test runs skip opt-in PTY, Docker, and real-agent suites; real-agent tests can launch paid services. Report skipped or unavailable verification. - CI tests that Semgrep rules work on fixtures; it does not scan the repository with Semgrep.
npm run lint:securityandnpm run lint:secretsrun separate scans and require Semgrep and Gitleaks respectively. - happy-dom cannot verify native Electron views. For browser-preview changes, follow the native smoke checks in
docs/browser-preview.md.
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 Changed · +147 tokens per session 443d102198c2
- 4d ago Changed · +9 lines · +381 tokens per session d9fcb90939c8
- 5d ago Changed · +1 lines · +56 tokens per session 6381f0d440d5
- 15d ago Changed · +1 lines · +103 tokens per session 6a1cfaf08cca
- 18d ago Changed · +5 lines · +127 tokens per session 58d749547eab
- 20d ago Changed · +1 lines · +48 tokens per session 95b3151524e1
- 1mo ago First seen · 59 lines · 1,271 tokens per session scan A e51977a48963
parallel-code AGENTS.md is an instructions file published in the GitHub repository johannesjo/parallel-code (1,065 stars, last pushed yesterday), licensed MIT. It adds 2,133 tokens to every session, about $0.0085 per session on Opus 5.5. 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 2026-09-16.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.