agentleFS
wheslleyrimarwheslleyrimar/BuildCLI-Agents/.github/copilot-instructions.md

BuildCLI-Agents

Copilot instructions3 starsChanged 11 days agoMITView on GitHub

A project-local executable at .buildcli/runtime/bcx (needs python3). Prefer it over reading state files by hand: Every agent on this project reads and writes the same files: Skills live in .github/skills/. Copilot Agent Mode discovers and activates them when the prompt matches their domain — no manual loading. Copilot has no native slash commands. These are prompt templates: open the file and paste it into Copilot Chat to run the stage. Bootstrap command: ./buildcli/scripts/bootstrap.sh --repo . --agent all --mode copy <!--…

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

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every agent on this project reads and writes the same files:

    line 19
  2. Very specific:

    Run the survey prompt first to create or refresh .buildcli/context.md.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 3,669 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

<!-- buildcli:autoload:start -->

Runtime

A project-local executable at .buildcli/runtime/bcx (needs python3). Prefer it over reading state files by hand:

  • .buildcli/runtime/bcx band <name> — load exactly one context band
  • .buildcli/runtime/bcx next — units ready to start, grouped by band
  • .buildcli/runtime/bcx graph — dependency graph and cycle report
  • .buildcli/runtime/bcx claim|done|block <id> — unit state transitions
  • .buildcli/runtime/bcx verify — run the project's test command
  • .buildcli/runtime/bcx resume — where the project left off, in one screen
  • .buildcli/runtime/bcx doctor — validate context, graph, and configuration

Shared state

Every agent on this project reads and writes the same files:

  • .buildcli/context.md — project context, split into independently loadable [band:*] blocks
  • .buildcli/active — path to the active blueprint directory
  • blueprints/<kind>/<slug>/brief.md — requirements and acceptance criteria
  • blueprints/<kind>/<slug>/shape.md — technical plan
  • blueprints/<kind>/<slug>/worklist.md — atomic units with band tags
  • blueprints/<kind>/<slug>/audit.md — verdict per acceptance criterion

Band skills (auto-discovered)

Skills live in .github/skills/. Copilot Agent Mode discovers and activates them when the prompt matches their domain — no manual loading.

  • .github/skills/service/SKILL.md
  • .github/skills/interface/SKILL.md
  • .github/skills/store/SKILL.md
  • .github/skills/verify/SKILL.md
  • .github/skills/delivery/SKILL.md

Workflow prompts

Copilot has no native slash commands. These are prompt templates: open the file and paste it into Copilot Chat to run the stage.

  • .copilot/commands/survey.md → profile the repo into .buildcli/context.md
  • .copilot/commands/brief.md → requirements with acceptance criteria
  • .copilot/commands/shape.md → architecture and a phased plan
  • .copilot/commands/worklist.md → atomic units with dependencies and band tags
  • .copilot/commands/build.md → execute the worklist band by band
  • .copilot/commands/patch.md → minimal defect fix (add --trace for a blueprint)
  • .copilot/commands/pulse.md → pipeline snapshot
  • .copilot/commands/focus.md → move the active blueprint pointer
  • .copilot/commands/mcp-add.md → add an MCP server to .vscode/mcp.json

Startup behavior (required)

  1. Run the survey prompt first to create or refresh .buildcli/context.md.
  2. Band skills in .github/skills/ activate automatically in Agent Mode.
  3. Each band skill names the exact block of .buildcli/context.md to read. Read that block, nothing else.
  4. Missing critical information → mark NEEDS CLARIFICATION and continue on safe defaults.

Multi-agent relay

  • survey + brief + shape → an analysis-focused agent
  • build → a code-generation agent
  • Handoff happens through blueprints/<kind>/<slug>/, tracked by .buildcli/active

Notes

  • Band skills are model-agnostic — they work with whatever model backs Copilot.
  • Auto-discovery needs Agent Mode (VS Code). In regular chat, paste the skill content by hand.

Bootstrap command: ./buildcli/scripts/bootstrap.sh --repo . --agent all --mode copy

<!-- buildcli:autoload:end -->

Download now (ZIP)

  • 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 2,297 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 repository19 other files it gives its agents.

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.