CowboyLogic/ai-dev / skills/client-config-copilotcli
client-config-copilotcli
UnverifiedManage GitHub Copilot CLI configuration files including settings.json, config.json, permissions-config.json, mcp-config.json, lsp-config.json, hooks, skills, custom agents, plugins, and custom instructions. Use this skill whenever the user wants to view, edit, add, or understand any Copilot CLI setting: trusted folders, user or repository settings, tool permissions, sandboxing, MCP or LSP servers, hooks, skills, custom agents, plugins and marketplaces, BYOK models, authentication, session management, or custom instructions. Trigger on: "add trusted folder", "allow tool", "configure MCP", "add hook", "create skill", "create agent", "install plugin", "set model", "use my own API key", "add custom instructions", "name session", "resume session", or "show my copilot config".
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 19.4 KB |
| README.md | markdown | 2.3 KB |
| SKILL.md | skill md | 7.6 KB |
| references/agents-plugins.md | markdown | 11.5 KB |
| references/cli-commands.md | markdown | 15.2 KB |
| references/config-schema.md | markdown | 37.2 KB |
| references/hooks.md | markdown | 15.6 KB |
| references/instructions.md | markdown | 4.1 KB |
| references/mcp.md | markdown | 12.1 KB |
| references/permissions.md | markdown | 22.8 KB |
| references/skills.md | markdown | 5.8 KB |
| scripts/show-config.py | script | 14.5 KB |
| scripts/update-references.py | script | 5.6 KB |
| sources.json | config | 12.2 KB |
references/instructions.md
View on GitHub# Custom Instructions Reference
Custom instructions give Copilot persistent context. All applicable files are **combined**; none
replaces another.
## Locations
"Standard locations" = the repository root, the cwd, intermediate directories between them, and
directories nested in the path of a file being worked on.
| File | Scope | Notes |
|------|-------|-------|
| `$HOME/.copilot/copilot-instructions.md` | Personal, all repos | `$COPILOT_HOME` replaces `$HOME/.copilot` |
| `$HOME/.copilot/instructions/**/*.instructions.md` | Personal, modular | Matched by `applyTo` |
| `.github/copilot-instructions.md` | Repository-wide | Standard locations |
| `.github/instructions/**/*.instructions.md` | Path-specific | Standard locations, **not** intermediate dirs |
| `AGENTS.md` | Repository-wide | Standard locations |
| `CLAUDE.md` | Repository-wide | Standard locations; `.claude/CLAUDE.md` also read |
| `GEMINI.md` | Repository-wide | Standard locations |
| Dirs in `COPILOT_CUSTOM_INSTRUCTIONS_DIRS` | Additional | Comma-separated; scanned for `AGENTS.md` and `*.instructions.md` |
- `/instructions` shows discovered files and toggles individual ones; `copilot instruction list
[--json]` lists them from the terminal.
- `--no-custom-instructions` disables loading `AGENTS.md` and related files.
- `copilot init` or `/init` generates or improves `.github/copilot-instructions.md`
(`/init suppress` hides the "No copilot instructions found" hint for the repo).
### How files combine
No general precedence between `copilot-instructions.md`, `AGENTS.md`, `CLAUDE.md`, and `GEMINI.md`.
Identical copies are deduplicated; conflicting instructions resolve non-deterministically — avoid
them. Path-specific files are included only when `applyTo` matches a file in context; files
disabled via `/instructions` are excluded. Path-specific rules at the repository root and in the
working directory are delivered automatically when the agent reads or edits a matching file.
### Subagents
Custom agents running as subagents don't receive repository instructions unless their frontmatter
sets `include-custom-instructions: true` (see `agents-plugins.md`). The `general-purpose` subagent
does receive them.
### Referencing other files
In `.github/copilot-instructions.md`, `AGENTS.md`, or `CLAUDE.md`, a line starting with `@` followed
by a relative path inlines that file (recursively, with depth, cycle, and size guards). The how-to
guide says referenced files must stay inside the repo (or the personal instructions directory) and
that absolute and `~/` paths are not loaded. `@` references are **not** expanded in `GEMINI.md` or
`*.instructions.md`.
> [!NOTE]
> The command reference says import paths "can be relative to the instruction file's directory or
> absolute", which contradicts the how-to guide. Prefer relative paths inside the repository.
### Live reload
Edits don't reach a running session. Exit and resume (`copilot --continue`) or start fresh (`/new`).
---
## Format
### Repository-wide (plain Markdown, no frontmatter)
```markdown
# Project Guidelines
- Use TypeScript strict mode
- Jest for unit tests, Playwright for e2e
- Conventional commits
```
### Path-specific (YAML frontmatter required)
```markdown
---
applyTo: "app/models/**/*.rb"
excludeAgent: "code-review"
---
# Rails Model Guidelines
- Use Active Record scopes for reusable queries
```
| Field | Description |
|-------|-------------|
| `applyTo` | Glob(s), comma-separated, e.g. `"**/*.ts,**/*.tsx"` |
| `excludeAgent` | `"code-review"` or `"cloud-agent"` — excludes that GitHub.com agent; omitted = used by both |
Glob quick reference: `*` (files in current dir), `**` or `**/*` (everything), `*.py` (current dir
only), `**/*.py` (recursive), `src/*.py` (non-recursive in `src/`), `src/**/*.py` (recursive under
`src/`), `**/subdir/**/*.py` (`subdir` at any depth).
---
## What to put where
- Instructions: architecture, conventions, preferred libraries, test commands, git workflow,
security rules — short guidance relevant to nearly every task.
- Skills: detailed task-specific procedures (see `skills.md`).
- Avoid duplicating or contradicting content across instruction files.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |