TypingMindTypingMindThe best frontend for AI
Dev Mode Init logo

Dev Mode Init

Community
jmagly
dev-mode-init

Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent

Overview

Publisherjmagly
Repositoryaiwg
Skill namedev-mode-init
Stars
225
Forks
34
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jmagly on GitHub. Read the source before you install it.

Installation

Install the Dev Mode Init AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-dev/skills/dev-mode-init
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jmagly/aiwg.git /tmp/aiwg
mkdir -p .claude/skills
cp -r /tmp/aiwg/agentic/code/addons/aiwg-dev/skills/dev-mode-init .claude/skills/dev-mode-init
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dev Mode Init in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dev Mode Init on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dev Mode Init is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dev Mode Init

You activate AIWG dev mode, rebuild the local source, deploy the developer toolkit, and run a dev health check. All operations go through the AIWG Steward agent and CLI — no direct file writes.

Triggers

  • "switch to dev mode" → full dev mode bootstrap
  • "aiwg use dev" → full dev mode bootstrap
  • "activate dev mode" → full dev mode bootstrap
  • "use local repo source" → switch CLI to dev + build
  • "switch back to stable" → deactivate dev mode
  • "rebuild and redeploy dev" → build + redeploy aiwg-dev without switching mode

Trigger Patterns Reference

PatternExampleAction
Full init"switch to dev mode"All steps
From repo path"use dev mode at ~/dev/aiwg"Switch + build from path
Stable"switch back to stable"aiwg --use-stable
Rebuild only"rebuild dev"Build + redeploy, skip mode switch
Check mode"am I in dev mode?"aiwg version + report

Process

Step 1 — Resolve repo path

If the user supplied a path, use it. Otherwise default to the current working directory.

bash
# Verify the target looks like the AIWG repo
ls package.json src/ agentic/ 2>/dev/null

If package.json is not found, stop and report: "Directory does not appear to be an AIWG repo — no package.json found."

Step 2 — Switch CLI to dev mode

bash
aiwg --use-dev <resolved-path>

Expected output confirms: Switched to dev mode. Dev repo: <path>

If already in dev mode pointing at the same path, skip and note "already in dev mode".

Step 3 — Build local source

bash
# TypeScript compile + web app build
npm run build

On failure: report the tsc or vite error, stop, and suggest running npm run build manually to see full output. Do not proceed past a broken build.

On success: note build time and output sizes (xterm, index bundles).

Step 4 — Deploy aiwg-dev addon (with Steward)

bash
aiwg use aiwg-dev

This deploys:

  • Steward agent (via aiwg-utils dependency)
  • Dev rules (skill-placement, no-circular-skill-calls, component-completeness, addon-boundaries)
  • Dev skills (dev-doctor, devkit-create-*, devkit-validate, devkit-test)

Step 5 — Dev health check

Invoke dev-doctor for a fast structural check:

bash
# TypeScript gate (already passed in step 3, but double-check deployed state)
npx tsc --noEmit

Then trigger /dev-doctor or report inline:

bash
# Run dev doctor sections 1–3 (structure, orphans, placement)
# Full run happens via aiwg dev-doctor or the dev-doctor skill

Step 6 — Report

markdown
## Dev Mode Init — Complete

**Mode**: dev [active]
**Repo**: <path>
**Build**: <duration> — xterm <size>, index <size>
**Deployed**: aiwg-dev (steward + dev tools)

### Status
- CLI mode:    ✓ dev
- Build:       ✓ clean (0 errors)
- Deployment:  ✓ aiwg-dev
- TypeScript:  ✓ passes

### Available
- `@aiwg-steward` — upgrade, sync, health check, capability routing
- `/dev-doctor` — structural health check
- `/devkit-create-*` — scaffolding tools
- `aiwg serve --no-open` + `cd apps/web && npm run dev` — live dashboard

### To switch back
`aiwg --use-stable`

Deactivation (switch back to stable)

When user requests stable mode:

bash
aiwg --use-stable

Report: "Switched back to stable npm package. Run aiwg sync to ensure frameworks are current."

Examples

Example 1: Full bootstrap from repo root

User: "switch to dev mode"

Action:

  1. Detect CWD is /home/user/dev/aiwg with package.json present
  2. Run aiwg --use-dev /home/user/dev/aiwg
  3. Run npm run build — succeeds in 8s
  4. Run aiwg use aiwg-dev
  5. Run npx tsc --noEmit — 0 errors

Output:

Dev Mode Init — Complete

Mode: dev [active] — /home/user/dev/aiwg
Build: 8.2s — xterm 291KB, index 246KB
Deployed: aiwg-dev (steward, 5 rules, 11 skills)
TypeScript: 0 errors

@aiwg-steward is ready. Use it for upgrades, syncs, and health checks.

Example 2: Path specified

User: "activate dev mode at ~/dev/aiwg"

Action: Run aiwg --use-dev ~/dev/aiwg → build → deploy → doctor

Example 3: Already in dev mode

User: "switch to dev mode"

Aiwg version shows: 2026.4.0-rc.26 [dev] path: /home/user/dev/aiwg

Action: Skip step 2. Still run build (source may have changed) and redeploy.

Output: "Already in dev mode. Rebuilding and redeploying..."

Example 4: Broken build

User: "switch to dev mode"

npm run build fails with TypeScript errors

Output:

Dev Mode Init — BLOCKED

Step 3 (build) failed. Fix TypeScript errors before proceeding.

Errors:
  src/serve/pty-bridge.ts(210,5): error TS2345: ...

Run `npm run build` to see full output.
Dev mode flag was set — run `aiwg --use-stable` to revert if needed.

References

  • @$AIWG_ROOT/agentic/code/addons/aiwg-dev/skills/dev-doctor/SKILL.md — Dev structural health check
  • @$AIWG_ROOT/agentic/code/addons/aiwg-utils/agents/aiwg-steward.md — Steward agent (maintenance + upgrades)
  • @$AIWG_ROOT/docs/development/aiwg-development-guide.md — Full dev workflow guide
  • @$AIWG_ROOT/docs/development/dev-testing.md — Dev testing patterns

Frequently asked questions

What does the Dev Mode Init AI skill do?

Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent

Why use Dev Mode Init on TypingMind?

Because you install it once and use it with any model. Dev Mode Init is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dev Mode Init in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/aiwg-dev/skills/dev-mode-init. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dev Mode Init?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dev Mode Init?

As many as you like. As long as a model supports skills, you can use Dev Mode Init with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dev Mode Init AI skill free?

Yes. It is published on GitHub by jmagly under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Graincrawl

openclaw
OrganizationPopular

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

82.2K
391K
1 files
View
openclaw logo

Openclaw Changelog Update

openclaw
OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

82.2K
391K
1 files
View
openclaw logo

Openclaw Ci Limits

openclaw
OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

82.2K
391K
1 files
View
openclaw logo

Openclaw Debugging

openclaw
OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇