setup
Skill0 starsChanged 3 months agoMITView on GitHub
Provider-neutral project bootstrap and OpenCode workflow configuration. Load when the user asks to set up a new project, configure providers or models via /connect, prepare an existing repo for this workflow, or writes a project-local AGENTS.md.
- Reads credentials
191 other projects use a version of this.
Adopted by
Most recently taken up by
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-voice-transcription, add-discord and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 7 projects that use this
- +8 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- data-workSkill
- frontend-designSkill
- geospatialSkill
- git-workflowSkill
- project-contractSkill
- python-devops-stackSkill
- research-protocolSkill
- review-protocolSkill
- test-qualitySkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Run or point to OpenCode's native /connect command to authenticate providers.
- Very specific: line 22
Verify the global config layout: agents/, commands/, and skills/ directories are discoverable from the OpenCode global config directory …
- Very specific: line 23
Never write provider names, model IDs, API keys, base URLs, or environment-variable names into any config file.
- Distinctive: line 51
Never: add planning-service references, session-state files, provider/model IDs, or personal paths.
- Distinctive: line 110
Only when the user confirms it, and the repository is Python:
- Very specific: line 158
After setup, offer once: "Set up a project contract?" Default is no (not-required).
- Distinctive: line 163
No credentials, provider names, model IDs, or MCP configuration are ever written by this skill.
“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Setup
Provider-neutral project bootstrap and OpenCode workflow configuration. It installs no provider or model settings, writes no credentials, and never mutates a project before explicit user confirmation.
When to load
- The user asks to set up a new project, configure their OpenCode provider/model setup, or prepare an existing repo for this workflow.
- The user runs
/setup.
Two modes
1. Workflow mode
Guide the user through configuring their own provider and model:
- Run or point to OpenCode's native
/connectcommand to authenticate providers. OpenCode stores credentials in its own auth store; do not read or write credential values. - Verify the global config layout:
agents/,commands/, andskills/directories are discoverable from the OpenCode global config directory (see opencode.ai/docs/config for the platform-specific location). - Never write provider names, model IDs, API keys, base URLs, or environment-variable names into any config file. The kit stays provider-neutral; the user's
opencode.jsonis their own.
2. Project mode
Bootstrap or migrate a project directory.
Detect
| Signal | Branch |
Directory empty or only .git/.gitignore present | New project |
.git exists with files, or files present without .git | Existing repo |
Interview (max 4 questions)
- Project name and one-line purpose.
- Delivery profile:
quick,standard,production, orpublished. - Git remote URL, or "local only".
- For Python projects: package name and whether the normalized Python route should be applied.
Propose and confirm
Present the exact set of files to create or merge and wait for explicit confirmation before any mutation. On an overwrite conflict with an existing file, stop and ask — never overwrite silently.
Compose project-local AGENTS.md
Compose from the target-file blocks below. For an existing project, merge the structural sections into any existing AGENTS.md — keep existing project-specific content, add the missing structural sections. For new projects, write the full file.
Never add planning-service references, session-state files, provider/model IDs, or personal paths.
Target file: AGENTS.md
# <Project Name>
<Project purpose — one sentence>
## Delivery Profile
`<Delivery Profile>` — determined during setup.
- branch/commit/PR workflow → load `git-workflow` skill
- profile-specific gates → see below
## Tech Stack
- <detected or chosen stack, e.g. Python + uv, Node + pnpm>
- <key libraries and tooling>
## Structure
<project layout, e.g. src/<package>/ and tests/ for Python>
## Toolchain & Workflow
- <package manager / validation commands for this stack>
- Validation and toolchain decisions → load `python-devops-stack` skill (Python projects).
- Branch / commit / PR workflow → load `git-workflow` skill.
## Conventions
- follow existing patterns before introducing new ones
- keep it simple — build only what the project needs
## Secrets
When present, `.env.example` declares expected variable names.
Never commit secret values.
## Known Constraints
<!-- durable constraints agreed during setup are added here -->
## Project Contract
Status: not-required
Manifest: TECHNICAL_CONTRACT.md
Activation reason: none
Opt-out reason: none
<!-- Set to active only on explicit request: "set up a project contract". Never automatic. -->Normalized Python route
Only when the user confirms it, and the repository is Python:
uv init # creates pyproject.toml, src/<pkg>/ layout when --package is used
uv add --dev ruff pytest
uv run ruff check .Profile gates:
| Profile | Gates added |
quick | uv + ruff only |
standard | pytest, optional pyright/nox |
production | mandatory pyright + nox validation entrypoint |
published | production gates + release ceremony via git-workflow (references/release.md) |
Target file: .gitignore (Python projects)
# Python
__pycache__/
*.py[cod]
.venv/
venv/
.nox/
.pytest_cache/
.ruff_cache/
.pyright/
*.egg-info/
build/
dist/
htmlcov/
.coverage
# Environment
.env
.env.*
!.env.example
# macOS
.DS_StoreFor non-Python projects, do not fabricate a stack. Recommend only what the detected files support (e.g. package.json → Node/pnpm) and defer details to the user's own tooling.
Compact project contract (opt-in)
After setup, offer once: "Set up a project contract?" Default is no (not-required). On acceptance, load the project-contract skill and establish a compact contract. It is never activated automatically by a delivery profile.
Rules
- Confirm before mutate. No mutation happens in workflow mode.
- No credentials, provider names, model IDs, or MCP configuration are ever written by this skill.
- Existing files are merged, never blindly replaced.
- Validation: after setup, verify the project config loads (
opencode --helpwith the project config) and, for Python,uv run nox(oruv run ruff check .when nox is not part of the profile) passes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

