Skip to content

CowboyLogic/ai-dev / skills/client-config-copilotcli

client-config-copilotcli

Unverified

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".

FileKindSize
CHANGELOG.mdmarkdown19.4 KB
README.mdmarkdown2.3 KB
SKILL.mdskill md7.6 KB
references/agents-plugins.mdmarkdown11.5 KB
references/cli-commands.mdmarkdown15.2 KB
references/config-schema.mdmarkdown37.2 KB
references/hooks.mdmarkdown15.6 KB
references/instructions.mdmarkdown4.1 KB
references/mcp.mdmarkdown12.1 KB
references/permissions.mdmarkdown22.8 KB
references/skills.mdmarkdown5.8 KB
scripts/show-config.pyscript14.5 KB
scripts/update-references.pyscript5.6 KB
sources.jsonconfig12.2 KB
# Copilot Configuration Manager

Manages GitHub Copilot CLI configuration: settings, permissions and sandboxing, MCP and LSP
servers, hooks, skills, custom agents, plugins, and instructions. The skill itself is
[SKILL.md](SKILL.md), and its history is in [CHANGELOG.md](CHANGELOG.md).

## Associated Copilot CLI version

| | |
|---|---|
| GitHub Copilot CLI | **v1.0.105** (released 2026-10-28, the latest stable release as of 2026-11-01) |
| References last refreshed | 2026-11-01 |
| Sources | docs.github.com Copilot CLI documentation (see [sources.json](sources.json)) and the [github/copilot-cli release notes](https://github.com/github/copilot-cli/releases) |

Claims that rest only on release notes, and not on the documentation, are labeled as such in the
reference files.

## Evaluation results

Benchmark run: **2026-04-26 · iteration 1** · 4 scenarios · 8 total runs

These results predate the 2026-09-24 v2.0 refresh and the 2026-10-11, 2026-10-12, 2026-10-13, 2026-10-14, 2026-10-18, 2026-10-25, and 2026-11-01 refreshes, and no benchmark has
been re-run since. The eval cases for this benchmark are not stored in the skill folder.

### Overall

| | With skill | Baseline (no skill) | Delta |
|---|---|---|---|
| Assertions passed | 20 / 20 | 6 / 20 | — |
| Pass rate | **100%** | **30%** | **+70 pp** |

### By scenario

| Scenario | With skill | Baseline | Delta | Notes |
|---|---|---|---|---|
| Add PostgreSQL MCP server | 5 / 5 | 4 / 5 | +20% | Baseline used wrong field name (`allowedTools` → `tools`) and omitted `type` field |
| HTTP audit hook (shell events only) | 6 / 6 | 2 / 6 | +67% | Baseline invented event name, wrong file path, wrong filter field, missing `version` field |
| Session naming + auto-switch (`--name`, `--resume`, `continueOnAutoMode`) | 4 / 4 | 0 / 4 | +100% | Baseline stated these features don't exist |
| BYOK Anthropic Claude Opus (`COPILOT_PROVIDER_*` env vars) | 5 / 5 | 0 / 5 | +100% | Baseline used wrong env vars and a non-existent `settings.json` model block |

### Key takeaway

The two largest gaps — session management and BYOK — are features added in
v1.0.35 that postdate the model's training data. The baseline doesn't give partial
answers for these; it confidently tells the user the features don't exist. The
skill closes that gap entirely.
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: 469kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall