Agent skill

Feature Flags

Creating and using feature flags in sidecar for gating experimental functionality.

MITAuto-check passed

Install Feature Flags

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/feature-flags .claude/skills/feature-flags && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .claude/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/feature-flags .agents/skills/feature-flags && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .agents/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/feature-flags .cursor/skills/feature-flags && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .cursor/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/marcus/sidecar.git --path .claude/skills/feature-flags

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/feature-flags .gemini/skills/feature-flags && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .gemini/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/feature-flags .github/skills/feature-flags && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .github/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add marcus/sidecar --skill feature-flags -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install marcus/sidecar feature-flags --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/marcus/sidecar.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/feature-flags .opencode/skills/feature-flags && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "feature-flags" agent skill from https://github.com/marcus/sidecar/tree/main/.claude/skills/feature-flags into .opencode/skills/feature-flags/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-flags", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: feature-flags
GitHub stars: 1.1k
Token cost: ~1.3k tokens
SKILL.md length: 440 words
Files: 1
Skills in repo: 19
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Creating and using feature flags in sidecar for gating experimental functionality.

Works in 3 steps: Define the feature in… → Add to the allFeatures slice → Use the feature check in your code
Adding feature flags
SKILL.md covers Checking Feature State, Adding a New Feature Flag, Giving a flag better copy… and User Configuration, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feature Flags is an agent skill from marcus/sidecar. Creating and using feature flags in sidecar for gating experimental functionality. Covers flag registration, checking flags in code, config file and CLI overrides, and priority resolution. Use when adding feature flags, toggling features, or gating new functionality behind flags.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td. The licence is MIT.

When your agent uses it

Adding feature flags
Toggling features
Gating new functionality behind flags

Example prompts

“/feature-flags”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Define the feature in internal/features/features.go
Add to the allFeatures slice
Use the feature check in your code

What it can do on your machine

Read from SKILL.md and the folder at commit 2a2978a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are go, json and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feature Flags loads about 1.3k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 440 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~74
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from marcus/sidecar at commit 2a2978a, republished under its MIT licence (© marcus). 440 words, ~1,275 tokens.

Download SKILL.mdSave it as .claude/skills/feature-flags/SKILL.md (or your agent's skills folder).

name: feature-flags
description: Creating and using feature flags in sidecar for gating experimental functionality. Covers flag registration, checking flags in code, config file and CLI overrides, and priority resolution. Use when adding feature flags, toggling features, or gating new functionality behind flags.
user-invocable: false

Feature Flags

Feature flags gate experimental functionality behind user-configurable settings, enabling safe rollout (default off), user opt-in, and easy rollback.

Checking Feature State

import "github.com/marcus/sidecar/internal/features"

if features.IsEnabled("tmux_interactive_input") {
    // Feature-gated code
}

Adding a New Feature Flag

Define the feature in internal/features/features.go:

var MyNewFeature = Feature{
    Name:        "my_new_feature",
    Default:     false,
    Description: "Description of what this enables",
}

Add to the allFeatures slice:

var allFeatures = []Feature{
    TmuxInteractiveInput,
    MyNewFeature, // Add here
}

Use the feature check in your code:

if features.IsEnabled("my_new_feature") {
    // New functionality
}

That is all a flag needs to be reachable. Configuration → System → Feature Flags derives its list from features.ListAll(), so registering a feature puts a working switch on the page with the registry's own Name as the label and Description as the help text. There is no second list to remember.

Giving a flag better copy (optional)

previewCopy in internal/configui/page_flags.go overrides the registry's wording per flag. Only fill in what you want to change:

features.MyNewFeature.Name: {
    label:   "Human-readable name",
    help:    "One sentence on what turning this on does.",
    restart: true, // only if a consumer reads it once at startup
    note:    "An honest scope line for a flag that applies live but not retroactively.",
},

restart must be checked against what actually consumes the flag, never added as blanket caution — a flag read at the point of use applies immediately and must not claim otherwise. Both restart and note render when both are set.

A flag that another page already owns as a first-class setting sets owner and ownerControl instead. It is then listed read-only with a jump to the control that owns it, because two switches over one value is how surfaces start disagreeing. If the owning page's control means more than the raw flag — Panels' Conversations switch is the flag and the plugin's own enabled key — also set reads so the row reports the owner's answer rather than the flag's.

Keep the page shorter than a small terminal. The Configuration detail pane truncates rather than scrolling, and the row cursor still walks onto rows that were cut. Rows are one line each with the explanation shown only under the focused row for that reason; TestFlagsPageFitsAnOrdinaryTerminal guards it.

Show full SKILL.md (155 more words)Show less

User Configuration

Config file (`~/.config/sidecar/config.json`)

json

{
  "features": {
    "flags": {
      "tmux_interactive_input": true
    }
  }
}

CLI override (takes precedence over config)

bash

sidecar --enable-feature=tmux_interactive_input
sidecar --disable-feature=tmux_interactive_input
sidecar --enable-feature=feature1,feature2   # Multiple features

Unknown feature names in CLI flags produce a warning but do not prevent startup.

Priority Order

Feature state resolves in this order (first match wins):

CLI override (--enable-feature, --disable-feature)
Config file (features.flags in config.json)
Default value (defined in code)

Available Features

Feature	Default	Description
`tmux_interactive_input`	true	Write support for tmux panes
`tmux_full_attach`	false	Suspend Sidecar and `tmux attach-session`
`tmux_inline_edit`	true	Inline file editing via tmux in files plugin
`notes_plugin`	true	Project Notes while the td panel is enabled
`tasks_plugin`	false	Embedded Tasks plugin tab
`conversations_plugin`	false	Conversations multi-agent history tab (off = no adapters / session I/O)
`workspace_terminal_panel`	true	Workspace Ctrl+T / Alt+T split terminal panel

API Reference

features.IsEnabled(name string) bool           // Check if enabled
features.List() map[string]bool                 // All features with current state
features.ListAll() []Feature                    // All features with metadata
features.SetEnabled(name string, enabled bool) error  // Persist to config
features.SetOverride(name string, enabled bool) // Runtime override (not persisted)
features.IsKnownFeature(name string) bool       // Check if registered

Best Practices

Use snake_case for feature names (e.g., my_new_feature)
New experimental features should default to false
Provide clear descriptions for each feature
Document features in docs/guides/deprecated/feature-flags.md when adding them
Remove feature flags once features are stable

Files

Just SKILL.md in .claude/skills/feature-flags of marcus/sidecar.

Open the folder on GitHubat commit 2a2978a

Compare with similar skills

Feature Flags next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feature Flags compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Feature Flags this skillmarcus/sidecar	1.1k	—	~1.3k	Automated safety check: Pass	MIT	today
Flagsvercel/next.js	143k	—	~746	Automated safety check: Pass	MIT	today
Gate Testsvercel/next.js	143k	—	~2.7k	Automated safety check: Pass	MIT	today
Feature Flagsgetsentry/sentry	46k	—	~374	Automated safety check: Pass	Custom licence	today
Gateplugin87/ux-ui-agent-skills	1.6k	—	~532	Automated safety check: Pass	MIT	yesterday
Setting Feature Flags In StorybookPostHog/posthog	40k	—	~1.1k	Automated safety check: Pass	Custom licence	today

Similar skills

Flags
vercel/next.js
Official
How to add or modify Next.js experimental feature flags end-to-end.
143k GitHub stars~746 tokensUpdated today
DevelopmentAuto-check passed
Gate Tests
vercel/next.js
Official
How to use the @gate / @force-gate test directives instead of it.skip or fake-green skip patterns.
143k GitHub stars~2.7k tokensUpdated today
Auto-check passed
Feature Flags
getsentry/sentry
Official
Gate a Sentry feature behind a FlagPole feature flag. An agent skill from getsentry/sentry.
46k GitHub stars~374 tokensUpdated today
Frontend & DesignAuto-check passed
Gate
plugin87/ux-ui-agent-skills
Run the one-command quality gate and report the real N/N result.
1.6k GitHub stars~532 tokensUpdated yesterday
Frontend & DesignAuto-check passed
Setting Feature Flags In Storybook
PostHog/posthog
Official
A skill your agent uses when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants.
40k GitHub stars~1.1k tokensUpdated today
Testing & QAAuto-check passed
Brain Ingest Gate
garrytan/gbrain
Pre-write quality gate for content entering the brain. An agent skill from garrytan/gbrain.
31k GitHub stars~3.9k tokensUpdated today
Testing & QAAuto-check passed

Questions about Feature Flags

What does Feature Flags do?

Creating and using feature flags in sidecar for gating experimental functionality. Feature Flags is an agent skill from marcus/sidecar. Creating and using feature flags in sidecar for gating experimental functionality.

When should I use Feature Flags?

Feature Flags fits situations like: adding feature flags; toggling features; gating new functionality behind flags.

How do I install Feature Flags in Claude Code?

Run `npx skills add marcus/sidecar --skill feature-flags -a claude-code`. Or copy the skill folder (.claude/skills/feature-flags in marcus/sidecar) into .claude/skills/feature-flags in your project. Claude Code loads it when a task matches its description.

How do I install Feature Flags in Codex?

Run `npx skills add marcus/sidecar --skill feature-flags -a codex`. Or copy the skill folder (.claude/skills/feature-flags in marcus/sidecar) into .agents/skills/feature-flags in your project. Codex loads it when a task matches its description.

Can I use Feature Flags in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add marcus/sidecar --skill feature-flags -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-flags, .gemini/skills/feature-flags, .github/skills/feature-flags and .opencode/skills/feature-flags in your project.

What does Feature Flags need to run?

SKILL.md names no scripts, command-line tools or credentials: Feature Flags is instructions for the agent only.

Does Feature Flags access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feature Flags safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Feature Flags use?

Feature Flags is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature Flags use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feature Flags?

Skills that share tags, products or a category with Feature Flags: Flags (vercel/next.js, 143k stars), Gate Tests (vercel/next.js, 143k stars), Feature Flags (getsentry/sentry, 46k stars) and Gate (plugin87/ux-ui-agent-skills, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature Flags?

marcus (a GitHub user) maintains it in marcus/sidecar, which has 1,086 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

Source: marcus/sidecar on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Feature Flags

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Feature Flags

Checking Feature State

Adding a New Feature Flag

Giving a flag better copy (optional)

User Configuration

Config file (~/.config/sidecar/config.json)

CLI override (takes precedence over config)

Priority Order

Available Features

API Reference

Best Practices

Files

Compare with similar skills

Similar skills

More from marcus/sidecar

Questions about Feature Flags

Config file (`~/.config/sidecar/config.json`)