Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/odysseus0/symphony/symphony-setupnpx skills add odysseus0/symphony --skill symphony-setupgit clone --depth 1 https://github.com/odysseus0/symphonyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/odysseus0/symphony/symphony-setup)<a href="https://agentmods.dev/skills/odysseus0/symphony/symphony-setup"><img src="https://agentmods.dev/badge/skills/odysseus0/symphony/symphony-setup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00079 | $0.02145 |
| Opus 5 | $0.00039 | $0.01073 |
| Sonnet 5 | $0.00016 | $0.00429 |
| Haiku 4.5 | $0.00008 | $0.00215 |
Grade C, and why
symphony-setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
6. **Git clone auth** — the `after_create` hook runs `git clone` unattended. Verify the user's repo clone URL works non-interactively: `git clone --depth 1 <url> /tmp/test-clone && rm -rf /tmp/test-clone`. HTTPS with pas Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
After the user picks a project, use Linear MCP to check the team's workflow states. Three custom states are required. If any are missing, create them via `curl`: How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Symphony Setup
Set up Symphony — OpenAI's orchestrator that turns Linear tickets into pull requests via autonomous Codex agents.
Preflight checks
Run these checks first and stop if any fail — resolve before continuing:
codex— runcodex --version. Must be installed and authenticated.mise— runmise --version. Needed for Elixir/Erlang version management.gh— rungh auth status. Must be installed AND authenticated. Agents useghto create PRs and close orphaned PRs. Silent failure without it.LINEAR_API_KEY— runtest -n "$LINEAR_API_KEY" && echo "set" || echo "missing". Must persist across sessions (shell config, not justexport).- Linear MCP — verify Linear MCP is available. If not, set it up:
- Claude Code:
claude mcp add --transport http linear https://mcp.linear.app/mcp - Codex:
codex mcp add linear --url https://mcp.linear.app/mcp - Other clients: see Linear MCP docs
- Claude Code:
- Git clone auth — the
after_createhook runsgit cloneunattended. Verify the user's repo clone URL works non-interactively:git clone --depth 1 <url> /tmp/test-clone && rm -rf /tmp/test-clone. HTTPS with password prompts will silently fail. Use SSH keys (no passphrase) or HTTPS with credential helper / token.
Report results to the user before proceeding.
Build Symphony
Use the fork — easier to get started with:
git clone https://github.com/odysseus0/symphony
cd symphony/elixir
mise trust && mise install
mise exec -- mix setup
mise exec -- mix build
Note: mise install downloads precompiled Erlang/Elixir if available for the platform. If not, it compiles from source — this can take 10-20 minutes. Let the user know before starting.
Prepare the user's repo
Auto-detect as much as possible. Only ask the user to confirm or fill gaps.
Auto-detect repo info
- Repo path —
git rev-parse --show-toplevelfrom the current directory. If not in a git repo, ask. - Clone URL —
git remote get-url origin. Verify it works non-interactively:git clone --depth 1 <url> /tmp/test-clone && rm -rf /tmp/test-clone. - Setup commands — infer from lockfiles/manifests. Confirm with the user.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 199 lines · 79 tokens per session scan C e18f70cfef87
symphony-setup is a skill published in the GitHub repository odysseus0/symphony (82 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,145 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It comes from a forked repository.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.