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 skills add cskwork/oh-my-symphony --skill symphony-skillgit clone --depth 1 https://github.com/cskwork/oh-my-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/cskwork/oh-my-symphony/symphony-skill)<a href="https://agentmods.dev/skills/cskwork/oh-my-symphony/symphony-skill"><img src="https://agentmods.dev/badge/skills/cskwork/oh-my-symphony/symphony-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 146 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 5.1 | $0.00055 | $0.02682 |
| Opus 5 | $0.00028 | $0.01341 |
| Sonnet 5 | $0.00011 | $0.00536 |
| Haiku 4.5 | $0.00006 | $0.00268 |
Grade A, and why
symphony-skill scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:9999/api/v1/state | jq How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Symphony
Symphony is a polling orchestrator that reads Kanban tickets and runs a coding-agent CLI (Codex, Claude Code, Gemini, AGY/Antigravity, Kiro, OpenCode, Pi, or Prime Agent) against each ticket in an isolated workspace. This file is the single operator router: classify the request, load only the matching reference, then act.
Start by reading the target WORKFLOW.md and one or two real kanban/*.md
files. Symphony behavior is workflow-specific, and forks commonly customize
lanes, prompts, hooks, workspace roots, and agent backends.
Route
State the route in one line, then open only the reference that route needs.
| Signal | Route | Read |
|---|---|---|
| create/register projects, open hub, add/list/show/move tickets, start service/TUI/API | OPERATE | reference/operations.md |
edit WORKFLOW.md, agent kind, hooks, prompts, workspace, Slack hooks |
CONFIGURE | reference/workflow-config.md |
| rename lanes, add state prompts, change pipeline shape | CUSTOMIZE | reference/customization.md |
| break a large request into Symphony board tickets | DELEGATE | reference/delegation.md |
| one prompt should become a full evidence-gated delivery pipeline | ONESHOT | oneshot/reference/operations.md |
| OneShot plan quality, ticket slicing, QA/PDF, vault, or lane gates | ONESHOT-DEEP | oneshot/reference/decomposition.md, then the needed OneShot reference |
| bootstrap Symphony into another repo | BOOTSTRAP | reference/bootstrapping.md |
| bootstrap isolated worktrees for a monorepo/polyrepo | MONOREPO | monorepo/references/workflow-template.md and monorepo/scripts/setup-monorepo.sh |
worker_exit, hook_failed, auth stall, blank TUI, stuck service |
TRIAGE | reference/troubleshooting.md |
| set up or debug Windows, macOS, Linux behavior | PLATFORM | reference/platform-compat.md |
.gitignore for Symphony-generated docs and logs |
GITIGNORE | reference/gitignore-recommendations.md |
Branch-specific subfolders under oneshot/ and monorepo/ intentionally do
not have their own SKILL.md. They provide templates, scripts, and deep
references for this router.
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- monorepo/references/workflow-template.md 3.7 KB
- monorepo/scripts/setup-monorepo.sh 4.3 KB runs code
- oneshot/reference/decomposition.md 8.3 KB
- oneshot/reference/lanes.md 15 KB
- oneshot/reference/operations.md 5.6 KB
- oneshot/reference/qa-browser.md 9.1 KB
- oneshot/reference/troubleshooting.md 6.0 KB
- oneshot/reference/vault.md 8.4 KB
- oneshot/templates/bootstrap.sh 6.5 KB runs code
- oneshot/templates/playwright-qa.spec.ts 6.3 KB runs code
- oneshot/templates/qa-pdf.sh 5.9 KB runs code
- oneshot/templates/SYSTEM.md 6.3 KB
- oneshot/templates/WORKFLOW.oneshot.md 24 KB
- reference/bootstrapping.md 5.2 KB
- reference/customization.md 6.5 KB
- reference/delegation.md 11 KB
- reference/gitignore-recommendations.md 3.1 KB
- reference/operations.md 10 KB
- reference/platform-compat.md 7.5 KB
- reference/troubleshooting.md 19 KB
- reference/workflow-config.md 25 KB
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.
- 7d ago First seen · 232 lines · 55 tokens per session scan A 4fb79739c34a
symphony-skill is a skill published in the GitHub repository cskwork/oh-my-symphony (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 2,682 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
kanban-board
A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.
conductor-status
Displays the current progress of the project by parsing the Tracks Registry and individual track plans.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.