agentleFS
Sign inStart free
DUBSOpenHubDUBSOpenHub/terminal-stampede/.github/copilot-instructions.md

terminal-stampede

Copilot instructions4 starsChanged 7 months agoMITView on GitHub

  • Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.

    Of the Copilot instructions files we read, the 2,343 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this copilot-instructions.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Filesystem as IPC: All coordination through .stampede/{run_id}/ directories inside the repo (queue, claimed, results, logs, pids).

    line 13
  2. Very specific:

    Python for JSON: All JSON operations use python3 -c 'import json.

    line 19
  3. Very specific:

    Keep the 24-landmine awareness — see SKILL.md's landmine reference table

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
copilot-instructions.md

Copilot Instructions for Terminal Stampede

What this project is

Terminal Stampede is a cross-terminal multi-agent orchestration framework. It splits work across independent AI coding agents running in parallel tmux panes, coordinated through a filesystem-based message queue. Built with GitHub Copilot CLI but designed to work with any CLI coding agent (Aider, Claude Code, etc.).

Architecture

Three files:

  • skills/SKILL.md — Orchestrator skill (YAML frontmatter + markdown instructions, Copilot CLI format)
  • agents/stampede-agent.agent.md — Worker agent (loaded per-session via --agent, Copilot CLI format)
  • bin/stampede.sh — Bash launcher (tmux session management, PID tracking, CLI-agnostic)

Key conventions

  • Filesystem as IPC. All coordination through .stampede/{run_id}/ directories inside the repo (queue, claimed, results, logs, pids). No databases, no HTTP, no Redis.
  • Atomic operations. Task claiming via mv (POSIX rename). Result writing via .tmp- prefix then mv. Race-safe by design.
  • CLI-agnostic launcher. stampede.sh defaults to Copilot CLI but supports --agent-cmd for any CLI agent.
  • Copilot-format skill/agents. The SKILL.md and agent markdown files use Copilot CLI's format. Other CLI agents use the shell scripts directly.
  • Branch per task. Workers create stampede/{task_id} branches. Never commit to main.
  • 500-word result cap. Worker summaries must be concise. Orchestrator context is limited.
  • Python for JSON. All JSON operations use python3 -c 'import json; ...'. Never echo/printf JSON in bash.

When editing these files

  • SKILL.md must keep valid YAML frontmatter with the tools: list
  • The worker agent must never include ask_user in its tools (it's autonomous)
  • The launcher must use -p with --autopilot (not -i) for autonomous worker execution
  • Keep the 24-landmine awareness — see SKILL.md's landmine reference table

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free