# AI use cases for OpenSpec (Fission-AI/OpenSpec)

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Use cases: 5 | Page: https://dedupedai.com/use-cases/fission-ai-openspec/

OpenSpec is a spec-driven development framework, installed as a CLI, that gives AI coding assistants a lightweight Markdown spec layer so humans and agents agree on what to build before code is written.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Plan a feature with an AI before any code is written: https://dedupedai.com/use-cases/fission-ai-openspec/plan-feature-with-ai-before-code/
- Switch to the expanded workflow and archive many changes at once: https://dedupedai.com/use-cases/fission-ai-openspec/run-expanded-workflow-and-bulk-archive/
- Share one plan across several repos with Stores: https://dedupedai.com/use-cases/fission-ai-openspec/share-cross-repo-plans-with-stores/
- Explore an idea with your AI before committing to a plan: https://dedupedai.com/use-cases/fission-ai-openspec/explore-an-idea-before-proposing-a-change/
- Keep OpenSpec current and its telemetry off: https://dedupedai.com/use-cases/fission-ai-openspec/turn-off-openspec-telemetry-and-update/

## How to plan a feature with an AI before any code is written with OpenSpec

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Explore, propose, apply, and archive one change so the agent builds only what you agreed to.

**Who it is for:** A developer working in an existing project who wants an AI coding assistant to add a feature but has unclear requirements and wants to review the plan first.

**The problem:** When requirements live only in chat history, AI coding output is vague and hard to predict.

**The outcome:** A change folder under openspec/changes/ with a proposal, specs, design, and tasks that you reviewed, plus code that matches those tasks and an archived record.

### Steps

1. Run `npm install -g @fission-ai/openspec@latest`
2. Run `cd your-project` and then `openspec init`
3. In your AI assistant, run `/opsx:explore` to shape the idea, then `/opsx:propose add-dark-mode` to create the change folder
4. Review proposal.md, the specs folder, design.md, and tasks.md before any code is written
5. Run `/opsx:apply` to implement the tasks, then `/opsx:archive` to move the change into the archive and update the specs

### Prompt to paste into your agent

```text
Using the OpenSpec repo at Fission-AI/OpenSpec, set up OpenSpec in <project-path> by running the install and `openspec init` steps, then use /opsx:explore and /opsx:propose <change-name> to create a change folder. Expected output: openspec/changes/<change-name>/ containing proposal.md, specs/, design.md, and tasks.md. Verify that the tasks file exists and summarize it for human review before running /opsx:apply.
```

### Caveat

The README says OpenSpec works best with high-reasoning models and a clean context window, so results depend on the model and session you use.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/fission-ai-openspec/plan-feature-with-ai-before-code/

## How to switch to the expanded workflow and archive many changes at once with OpenSpec

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Enable the full set of OpenSpec commands and clear finished changes in one pass.

**Who it is for:** A developer or team lead who has finished several changes in a project and wants to close them out together and use finer-grained commands.

**The problem:** Finished changes pile up in openspec/changes/ and each needs separate archiving when they are done one by one.

**The outcome:** The expanded command set is active in the project, and finished changes are archived in one bulk run with specs updated.

### Steps

1. Run `npm install -g @fission-ai/openspec@latest` to make sure the CLI is current
2. Run `openspec config profile` and select the expanded workflow
3. Run `openspec update` inside the project to regenerate agent instructions and activate the new slash commands
4. In your AI assistant, run `/opsx:verify` on each finished change, then run `/opsx:bulk-archive`

### Prompt to paste into your agent

```text
In the Fission-AI/OpenSpec project at <project-path>, select the expanded workflow with `openspec config profile`, then run `openspec update`. Expected output: the new commands such as /opsx:verify and /opsx:bulk-archive are listed as active for your assistant. Verify that openspec/changes/ lists the finished changes before running /opsx:bulk-archive.
```

### Caveat

The README says the expanded commands need profile selection and `openspec update`, and it does not describe how bulk archive chooses which changes to archive, so check the list before confirming.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/fission-ai-openspec/run-expanded-workflow-and-bulk-archive/

## How to share one plan across several repos with Stores with OpenSpec

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Keep cross-repo specs in a separate shared repo that code repos and agents can read.

**Who it is for:** A platform or product team whose feature spans an API server, a web app, and a shared library, and who wants one source of truth for requirements.

**The problem:** Requirements drift across repos and wikis, and a feature that touches several codebases has no single plan.

**The outcome:** A planning repo holding the shared openspec/ specs and changes, pushed with git, that your team and coding agents can read across repos.

### Steps

1. Read the Stores guide at https://openspec.dev/docs/stores, since Stores is in beta
2. Create a dedicated planning repo for the team and set up its openspec/ folder following the guide
3. Add the planning repo to each code repo's agent context as the guide describes (inferred, check the README)
4. Capture the cross-repo plan as a change in the store before the code repos are updated
5. Push the planning repo with `git push` so the whole team and every coding agent can read it

### Prompt to paste into your agent

```text
Using the Stores guide at openspec.dev/docs/stores for Fission-AI/OpenSpec, set up a planning repo at <store-path> with the openspec/ shape of specs and changes. Expected output: a committed store containing one cross-repo change folder. Verify that the change folder is present and pushed with git before any code repo is modified.
```

### Caveat

The README describes Stores as beta and points to the docs for setup, so the steps here stay at a high level and the guide is the source of truth.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/fission-ai-openspec/share-cross-repo-plans-with-stores/

## How to explore an idea with your AI before committing to a plan with OpenSpec

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README

Use /opsx:explore as a no-stakes thinking partner that reads your code and weighs options first.

**Who it is for:** A developer with a fuzzy feature idea, such as adding dark mode cleanly, who is not ready to write a spec.

**The problem:** Jumping straight to code with an AI on a vague idea produces messy, unscoped changes.

**The outcome:** A scoped approach agreed with your AI, ready to turn into a proposal with specs, design and tasks.

### Steps

1. Install with `curl -fsSL https://raw.githubusercontent.com/Fission-AI/OpenSpec/main/scripts/binary/install.sh | sh` (or `brew install openspec`)
2. Run openspec init in your project
3. Ask your AI /opsx:explore and describe the idea
4. Let it read your code, weigh options and propose a scope
5. When you agree, run /opsx:propose with a change name to create the proposal

### Prompt to paste into your agent

```text
Using Fission-AI/OpenSpec in this repo, run /opsx:explore on <idea>: read the relevant code, give me two or three approaches with tradeoffs, and only after I pick one, run /opsx:propose to create the change folder.
```

### Caveat

This card is written from the Fission-AI/OpenSpec README, not from a test run by Deduped. Before you start, make sure you have Node.js 20.19.0 or higher, or Homebrew on macOS or Linux. Check the repo for newer instructions before you rely on these steps.

Risk, remote script: The standalone install pipes a script from GitHub into sh; npm and Homebrew installs are alternatives.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/fission-ai-openspec/explore-an-idea-before-proposing-a-change/

## How to keep OpenSpec current and its telemetry off with OpenSpec

Repo: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) | Difficulty: Beginner | Time: 10 minutes | Basis: From the README

Upgrade the CLI, refresh agent instructions in each project and opt out of anonymous usage stats.

**Who it is for:** A team lead rolling OpenSpec out across repos who needs current slash commands and no telemetry.

**The problem:** Stale agent instructions miss new slash commands, and some teams must disable usage stats.

**The outcome:** An up-to-date CLI, regenerated AI guidance in each project and telemetry disabled.

### Steps

1. Upgrade the standalone CLI with openspec install, or `npm install -g @fission-ai/openspec@latest`, or `brew upgrade openspec`
2. Run openspec update inside each project to regenerate AI guidance
3. Opt out globally with `openspec config set telemetry.enabled false`
4. Or set `export OPENSPEC_TELEMETRY=0` in CI and shared environments
5. Check that the latest slash commands appear in your tool

### Prompt to paste into your agent

```text
Update Fission-AI/OpenSpec on this machine, run openspec update in each repo under <folder>, disable telemetry globally, and list the slash commands now available in my tool.
```

### Caveat

This card is written from the Fission-AI/OpenSpec README, not from a test run by Deduped. Before you start, make sure you have Node.js 20.19.0 or higher, or Homebrew on macOS or Linux. Check the repo for newer instructions before you rely on these steps.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/fission-ai-openspec/turn-off-openspec-telemetry-and-update/
