Codex symphony
Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.From its SKILL.md
npx -y skills add citedy/skills --skill codex-symphonyAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- reads credentialsReads from 2 credential sources: `LINEAR_API_KEY` and 1 more.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 8 commands, including `bash scripts/install.sh [optional-repo-path]` and 7 more.
SKILL.md
2.5 KB, 533 tokens by cl100k_base, as published. Nobody here has run it
Codex Symphony
Use this skill when the user wants to install or operate a local OpenAI Symphony setup for a repository.
When to Use
Use this skill when the user asks to:
- install Symphony into a repo
- restart Symphony after reopening Codex
- add a reusable
codex-symphonycommand - bootstrap Linear-driven agent orchestration
- create a portable Symphony package for another machine or repo
- diagnose why Symphony is not starting
- initialize repo-local Symphony env files safely
Core Rule
Do not assume a fixed repository path.
Always resolve the target repo by:
- explicit argument, if the user gave one
git rev-parse --show-toplevel, if running inside a repo- otherwise ask for the repo path
Install
Run the bundled installer:
bash scripts/install.sh [optional-repo-path]
The installer will:
- copy
WORKFLOW.symphony.md - copy
scripts/symphony/* - copy
.env.symphony.example - enable
./scripts/symphony/init.shfor.env.symphony.local - enable
./scripts/symphony/doctor.shfor readiness checks - append
.symphony/to.gitignoreif missing - install
~/.local/bin/codex-symphony - link this skill into
~/.codex/skills/codex-symphony
Operate
After install, the normal commands are:
./scripts/symphony/init.sh
./scripts/symphony/doctor.sh
codex-symphony
./scripts/symphony/logs.sh
./scripts/symphony/restart.sh
./scripts/symphony/start-background.sh
./scripts/symphony/status.sh
./scripts/symphony/stop.sh
Required Env
The target repo must provide:
LINEAR_API_KEYLINEAR_PROJECT_SLUGSOURCE_REPO_URLSYMPHONY_WORKSPACE_ROOT
Optional:
GH_TOKENSYMPHONY_PORT
Expected Help Pattern
When helping the user:
- run the installer if the repo is not bootstrapped yet
- prefer
./scripts/symphony/init.shover manual env editing - run
./scripts/symphony/doctor.shbefore starting if setup looks incomplete - tell the user which env vars or tools are still missing
- start Symphony only after the repo is configured
- report dashboard URL and log path only
What ships with it: 16 files
28.9 KB alongside SKILL.md, 2 of them executable
agents/
- openai.yaml269 B
assets/
- common.sh.template2.9 KB
- doctor.sh.template2.1 KB
- env.symphony.example134 B
- init.sh.template2.6 KB
- logs.sh.template237 B
- restart.sh.template202 B
- start-background.sh.template1.7 KB
- start-local.sh.template1.3 KB
- status.sh.template1.2 KB
- stop.sh.template752 B
- WORKFLOW.symphony.md.template6.0 KB
scripts/
- install.shruns3.9 KB
- self-test.shruns1.5 KB