client-config-copilotcli
Skill4 starsChanged 11 days agoMITView on GitHub
Manage 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".
- Commits and pushes
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/client-config-opencode/references/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- repository-reviewSkill
- weekly-skill-refreshSkill
- skill-maintenanceSkill
- about-me-skill-creatorSkill
- agent-creator-claudecodeSkill
- agent-creator-codexSkill
- agent-creator-copilotSkill
- agent-creator-opencodeSkill
- client-config-claudecodeSkill
- client-config-codexSkill
- client-config-opencodeSkill
- copilot-instruction-creatorSkill
- copilot-workerSkill
- docker-image-managementSkill
- git-commit-messagesSkill
- google-style-docsSkill
- handoffSkill
- markdownlint-validatorSkill
- mkdocs-site-managementSkill
- skill-routerSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Read the target file first: before making any changes
- Distinctive: line 129
When the user asks to update, refresh, or sync this skill:
- Very specific: line 131
Run python scripts/update-references.py --all → fetches each configured reference source to _fetched/
- Very specific: line 132
If the script exits nonzero, resolve the reported failures and rerun it.
- Very specific: line 133
Read each _fetched/ file alongside its corresponding references/ file
- Very specific: line 134
Update references/ files to reflect documentation changes
- Very specific: line 135
Delete _fetched/ and report what changed
- Distinctive: line 141
Always read the file before editing
- Very specific: line 142
Never remove trustedFolders entries without confirming with the user
- Very specific: line 144
Don't edit permissions-config.json while a Copilot CLI session is running
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.
Files
Copilot Configuration Manager
You help the user manage all GitHub Copilot CLI configuration files.
Config file map
| What | File | Scope |
| User settings (model, theme, URLs, hooks, ...) | ~/.copilot/settings.json | Global |
| Repository settings (limited keys) | .github/copilot/settings.json | Project (committed) |
| Local settings (limited keys) | .github/copilot/settings.local.json | Project (gitignored) |
| Trusted folders, auth state | ~/.copilot/config.json (trustedFolders) | Global |
| Saved tool/directory approvals | ~/.copilot/permissions-config.json | Global, per location |
| MCP servers | ~/.copilot/mcp-config.json | Global |
| MCP servers | .mcp.json or .github/mcp.json | Project |
| LSP servers | ~/.copilot/lsp-config.json / .github/lsp.json | Global / Project |
| BYOK providers | ~/.copilot/providers.json | Global |
| Hooks | ~/.copilot/hooks/<name>.json or hooks in settings.json | Global |
| Hooks | .github/hooks/<name>.json or hooks in repo settings | Project |
| Skills | ~/.copilot/skills/<name>/SKILL.md (or ~/.agents/skills/) | Global personal |
| Skills | .github/skills/, .agents/skills/, .claude/skills/ | Project |
| Custom agents | ~/.copilot/agents/<name>.agent.md | Global personal |
| Custom agents | .github/agents/ or .claude/agents/ | Project |
| Plugins | ~/.copilot/installed-plugins/ (manage via copilot plugin) | Global |
| Custom instructions | ~/.copilot/copilot-instructions.md, ~/.copilot/instructions/**/*.instructions.md | Global personal |
| Custom instructions | .github/copilot-instructions.md, AGENTS.md, CLAUDE.md, GEMINI.md | Project |
| Path-specific instructions | .github/instructions/**/*.instructions.md | Project (applyTo glob) |
| Model allowlist | .github/allowed_models.txt | Project |
Config directory override: set COPILOT_HOME to replace ~/.copilot entirely
(--config-dir is deprecated). User preferences belong in settings.json; user-setting keys left
in config.json are ignored, and config.json keeps only internal state such as trusted folders.
Workflow
- Identify the task → use the task-to-reference map below to load only what you need
- Read the target file first before making any changes
- Edit safely → use the Edit tool for targeted changes; validate JSON after editing
- Confirm → show the user exactly what changed
Task → Reference map (load only what's needed)
| Task | Reference file |
settings.json keys (user, repo, local), config directory layout | references/config-schema.md |
Trusted folders, config.json | references/config-schema.md §config.json |
| Environment variables | references/config-schema.md §Environment variables |
OpenTelemetry export, managed telemetry | references/config-schema.md §OpenTelemetry monitoring |
| Authentication, tokens | references/config-schema.md §Auth |
| BYOK models / custom providers, model selection | references/config-schema.md §BYOK, §Model usage |
Tool/path/URL permissions, permissions-config.json, sandbox, plan-mode and shell safety checks | references/permissions.md |
CLI flags, slash commands, supported model IDs, sessions (--name, --resume), debug logs | references/cli-commands.md |
| MCP servers, LSP servers | references/mcp.md |
| Hooks, including agent-scoped hooks in custom agent frontmatter | references/hooks.md |
| Skills | references/skills.md |
| Custom agents, subagents, plugins, marketplaces | references/agents-plugins.md |
| Custom instructions | references/instructions.md |
Common quick operations (no reference needed)
# Trust a folder permanently: add its path to "trustedFolders" in ~/.copilot/config.json
# Change a setting (inside a session)
/settings # editor; /settings KEY VALUE sets inline
/settings show model
# Read or change a setting from the terminal (user file by default; --repo / --local available)
copilot config theme
copilot config footer.showQuota off
copilot config --list
# Check auth
/user show # inside a session; copilot login to sign in
# MCP servers
copilot mcp list # terminal; /mcp list inside a session
# Skills
copilot skill list # terminal; /skills list inside a session
# Model
/model # inside a session; or copilot --model=auto
# Permissions for this session
copilot --allow-tool='shell(git:*)' --deny-tool='shell(git push)'
/allow-all # alias for /permissions allow-all
# Sandbox shell commands (macOS, Linux, Windows)
copilot --sandbox # this session only; /sandbox enable saves the setting
# Offline mode (BYOK only, no GitHub contact)
export COPILOT_OFFLINE=true
# Name and resume sessions
copilot --name my-feature-work
copilot --resume=my-feature-work
/session delete [ID] # or /session delete-all
# Prevent system sleep during long sessions
/keep-alive on # on | off | busy | DURATION
# Remote control (--no-remote is removed and --remote no longer works for interactive or -p startup; it remains only for legacy --server/--headless; remoteSessions: true makes it the default)
/remote on
/remote off
# Session-history syncing and client telemetry, one run only
copilot --sync-session=off
copilot --disable-client-telemetry
# What's loaded right now (instructions, MCP, skills, agents, hooks, plugins)
/envScripts
scripts/show-config.py— display all config files with annotationsscripts/update-references.py— fetch latest upstream docs
Run with: python scripts/<script>.py
Self-update procedure
When the user asks to update, refresh, or sync this skill:
- Run
python scripts/update-references.py --all→ fetches each configured reference source to_fetched/ - If the script exits nonzero, resolve the reported failures and rerun it; do not use a partial
_fetched/set as source material - Read each
_fetched/file alongside its correspondingreferences/file - Update
references/files to reflect documentation changes - Delete
_fetched/and report what changed
Source URLs are in sources.json.
Safety rules
- Always read the file before editing
- Never remove
trustedFoldersentries without confirming with the user - Hooks and skills live in project directories — confirm scope (global vs project) before creating
- Don't edit
permissions-config.jsonwhile a Copilot CLI session is running - JSON files: validate well-formed after any edit (
settings.jsonalso accepts JSONC comments) - Hook, instruction, and custom-agent changes apply only after restarting (or resuming) the CLI; skills, MCP, and LSP can use
/skills reload,/mcp reload,/lsp reload - Markdown files: preserve frontmatter structure
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
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.

