Kouchou AI Development
digitaldemocracy2030/kouchou-ai
Local development setup, build and lint commands, environment configuration, and deployment helpers for the kouchou-ai repo.
Declares each new or noticeable change as an off-by-default entry in OpenWork's feature registry before any feature code, and covers rollout, kill switches and cleanup.
Install OpenWork Feature Rollout
$ npx skills add different-ai/openwork --skill add-a-feature -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install different-ai/openwork add-a-feature --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/add-a-feature .claude/skills/add-a-feature && rm -rf skills-srcUse ~/.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/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .claude/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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 install https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-featureType 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.
$ npx skills add different-ai/openwork --skill add-a-feature -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install different-ai/openwork add-a-feature --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/add-a-feature .agents/skills/add-a-feature && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .agents/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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.
$ npx skills add different-ai/openwork --skill add-a-feature -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install different-ai/openwork add-a-feature --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/add-a-feature .cursor/skills/add-a-feature && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .cursor/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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 https://github.com/different-ai/openwork.git --path .opencode/skills/add-a-feature--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add different-ai/openwork --skill add-a-feature -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install different-ai/openwork add-a-feature --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/add-a-feature .gemini/skills/add-a-feature && rm -rf skills-srcUse ~/.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/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .gemini/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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.
$ gh skill install different-ai/openwork add-a-featureInstalls 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).
$ npx skills add different-ai/openwork --skill add-a-feature -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/add-a-feature .github/skills/add-a-feature && rm -rf skills-srcUse ~/.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/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .github/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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.
$ npx skills add different-ai/openwork --skill add-a-feature -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install different-ai/openwork add-a-feature --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/add-a-feature .opencode/skills/add-a-feature && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "add-a-feature" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/add-a-feature into .opencode/skills/add-a-feature/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-a-feature", 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
add-a-feature- GitHub stars
- 24k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 745 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Declares each new or noticeable change as an off-by-default entry in OpenWork's feature registry before any feature code, and covers rollout, kill switches and cleanup.
- Works in 4 steps: Declare it, off → Make it safe to turn off at any moment → Gate the code → …
- Starting any change in OpenWork that users would notice
- SKILL.md covers The model: one rollout,…, Does this need a feature?, 1. Declare it, off and 2. Make it safe to turn off at…, plus 4 more sections
- Calls pnpm
What it does
In the OpenWork repository, every user-visible feature and every change existing users would notice is declared in `packages/features/src/registry.ts` (package `@openwork/features`) before the feature code is written, and starts off. One function, `resolveFeature`, applies a fixed order: the deployments a feature exists on (cloud or self-hosted), a kill switch that turns it off everywhere with no deploy, a self-hosted operator lock set through Helm, an organization override set by admins in `/admin`, and an everyone setting.
The skill also says what is not a feature: bug fixes, copy changes, refactors, internal tooling, compatibility shims, values derived from configuration, and settings that change how something works rather than whether people get it. Keys are lowerCamelCase and permanent, since they also become the Helm key, a `DEN_FEATURE_` environment variable, the API field and stored rows. Rollouts can be changed in `/admin` or with the `den_list_features`, `den_set_feature_rollout` and `den_set_org_capability` MCP tools, and tests run with `pnpm --filter @openwork/features test`.
When your agent uses it
- Starting any change in OpenWork that users would notice
- Rolling a feature out per organization or for everyone
- Killing or reverting a shipped feature without a deploy
- Finishing or removing a rollout after launch
Example prompts
- “Add a new workspace templates screen to OpenWork behind a feature flag.”
- “Roll the new engine out to one organization first and keep it off for everyone else.”
- “Kill the experimental sidebar feature everywhere.”
Requirements
- A checkout of the OpenWork repository
- pnpm, to run the feature tests
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Declare it, off
- Make it safe to turn off at any moment
- Gate the code
- Roll it out
What it can do on your machine
Read from SKILL.md and the folder at commit 9ce20f8. 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
Shell commands in SKILL.md call:
pnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
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
OpenWork Feature Rollout loads about 1.4k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 745 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 745 words (~1,420 tokens).
“Every new user-visible feature, and every change existing users would notice, is a feature in the registry, declared before any feature code, off. Nothing big ships ungated.”
- name
- add-a-feature
Files
Just SKILL.md in .opencode/skills/add-a-feature of different-ai/openwork.
Open the folder on GitHubat commit 9ce20f8
Compare with similar skills
OpenWork Feature Rollout 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| OpenWork Feature Rollout this skilldifferent-ai/openwork | 24k | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Kouchou AI Developmentdigitaldemocracy2030/kouchou-ai | 171 | — | ~540 | Automated safety check: Notes | AGPL-3.0 | |
| TS SDK Authormindfold-ai/Trellis | 15k | — | ~6.1k | Automated safety check: Pass | MIT | |
| Releasecortex-tms/cortex-tms | 180 | — | ~398 | Automated safety check: Pass | MIT | |
| DeerFlow Smoke Testbytedance/deer-flow | 83k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Desktop Release Sync LandingEynzof/Hermes-CN-Desktop | 1.7k | — | ~1.3k | Automated safety check: Pass | Custom licence |
Similar skills
TS SDK Author
mindfold-ai/Trellis
Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo.
Release
cortex-tms/cortex-tms
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish.
DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
Desktop Release Sync Landing
Eynzof/Hermes-CN-Desktop
Use only for stable/public Hermes Agent CN Desktop releases that should be visible to all users.
- Official
Deploy Release Test
vercel/next.js
Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow.
More from different-ai/openwork
All 33 skills in this repoOpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
Fake Model Provider Faults
different-ai/openwork
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
OpenWork Model Alias Manager
different-ai/openwork
Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
OpenWork Electron Browser Automation
different-ai/openwork
Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.
Daytona Sandbox Operations
different-ai/openwork
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
Related
Works with
Categories
Questions about OpenWork Feature Rollout
What does OpenWork Feature Rollout do?
Declares each new or noticeable change as an off-by-default entry in OpenWork's feature registry before any feature code, and covers rollout, kill switches and cleanup. ts` (package `@openwork/features`) before the feature code is written, and starts off. One function, `resolveFeature`, applies a fixed order: the deployments a feature exists on (cloud or self-hosted), a kill switch that turns it off everywhere with no deploy, a self-hosted operator lock set through Helm, an organization override set by admins in `/admin`, and an everyone setting.
When should I use OpenWork Feature Rollout?
OpenWork Feature Rollout fits situations like: starting any change in OpenWork that users would notice; rolling a feature out per organization or for everyone; killing or reverting a shipped feature without a deploy; finishing or removing a rollout after launch.
How do I install OpenWork Feature Rollout in Claude Code?
Run `npx skills add different-ai/openwork --skill add-a-feature -a claude-code`. Or copy the skill folder (.opencode/skills/add-a-feature in different-ai/openwork) into .claude/skills/add-a-feature in your project. Claude Code loads it when a task matches its description.
How do I install OpenWork Feature Rollout in Codex?
Run `npx skills add different-ai/openwork --skill add-a-feature -a codex`. Or copy the skill folder (.opencode/skills/add-a-feature in different-ai/openwork) into .agents/skills/add-a-feature in your project. Codex loads it when a task matches its description.
Can I use OpenWork Feature Rollout 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 different-ai/openwork --skill add-a-feature -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-a-feature, .gemini/skills/add-a-feature, .github/skills/add-a-feature and .opencode/skills/add-a-feature in your project.
What does OpenWork Feature Rollout need to run?
Going by SKILL.md and its folder, OpenWork Feature Rollout needs the command-line tools its instructions call (pnpm). Our summary lists: A checkout of the OpenWork repository; pnpm, to run the feature tests.
Does OpenWork Feature Rollout 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 OpenWork Feature Rollout 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 OpenWork Feature Rollout use?
OpenWork Feature Rollout has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does OpenWork Feature Rollout use?
About 1.4k tokens (SKILL.md is roughly 5.7k 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 OpenWork Feature Rollout?
Skills that share tags, products or a category with OpenWork Feature Rollout: Kouchou AI Development (digitaldemocracy2030/kouchou-ai, 171 stars), TS SDK Author (mindfold-ai/Trellis, 15k stars), Release (cortex-tms/cortex-tms, 180 stars) and DeerFlow Smoke Test (bytedance/deer-flow, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains OpenWork Feature Rollout?
different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,943 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 8, 2026.
Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.