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 instructions/cskwork/oh-my-symphony/agents-mdgit 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/instructions/cskwork/oh-my-symphony/agents-md)<a href="https://agentmods.dev/instructions/cskwork/oh-my-symphony/agents-md"><img src="https://agentmods.dev/badge/instructions/cskwork/oh-my-symphony/agents-md.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 | $0.00762 | $0.00762 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
oh-my-symphony AGENTS.md scanned grade A with 0 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: Codex CLI entry point
This repo is Symphony, a polling orchestrator that dispatches coding
agents (Codex / Claude Code / Gemini / AGY / Kiro / OpenCode / Pi) at a Kanban board. This file is
the discovery point that Codex (and any other AGENTS.md-respecting CLI)
reads on startup. It gives the operator, meaning the human or agent running
symphony, the same skill guidance Claude Code gets from .claude/skills/.
Source of truth: skills/symphony-skill
Operator-side routing lives in one skill:
skills/symphony-skill/SKILL.md. It has YAML frontmatter (name,
description, optional triggers) and routes requests to the right reference
or support bundle. .claude/skills/ is a thin symlink layer for Claude Code's
native discovery. Do not edit through it. Edit the canonical files under
skills/.
skills/symphony-skill/oneshot/ and skills/symphony-skill/monorepo/ are
branch-specific subfolders with templates, scripts, and references used by the
router. They intentionally do not expose separate SKILL.md activation routes.
Available skill (operator-facing)
Load skills/symphony-skill/SKILL.md when the user's request matches the
trigger description below. Open only the reference page named by the router's
decision table.
symphony-skill
Use when the user wants to dispatch coding agents (Codex / Claude Code / Gemini / AGY / Kiro / OpenCode / Pi) against a Kanban board via this
oh-my-symphonyrepo — adding/listing/transitioning tickets, launching the TUI, inspecting orchestrator state, customizing the workflow (lanes, per-state prompts), delegating sub-tasks to free up context, one-shotting a prompt into an evidence-gated board, bootstrapping a monorepo workflow, or diagnosing dispatch failures. Triggers on phrases like "add a symphony task", "run symphony", "dispatch this ticket", "symphony board", "WORKFLOW.md", "symphony tui won't start", "ticket failed with worker_exit", "customize kanban states", "deploy pipeline workflow", "delegate to symphony", "agent.kind: pi", "agent silent for N seconds", "one-shot this", "decompose and dispatch with proof", or "symphony monorepo".
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.
- 4d ago First seen · 62 lines · 762 tokens per session scan A ab3771bdfd08
oh-my-symphony AGENTS.md is an instructions file published in the GitHub repository cskwork/oh-my-symphony (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 762 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
kaneo CLAUDE.md
Claude Code instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
veritas-kanban AGENTS.md
AGENTS.md instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.
agtx CLAUDE.md
Claude Code instructions for fynnfluegge/agtx, covering agtx - terminal kanban for coding agents, quick start, build, run in a git project directory and or run in dashboard mode (no git project required).
veritas-kanban CLAUDE.md
Claude Code instructions for BradGroux/veritas-kanban, covering claude.md — claude-specific supplement for veritas kanban, what changed in v2.1, lessons learned (claude-specific), security and architecture.
kanban CLAUDE.md
Claude Code instructions for kanban-rs/kanban, covering claude.md, project overview, architecture philosophy, solid principles applied and workspace structure.
kanban-md AGENTS.md
Instructions for antopolskiy/kanban-md, covering guidelines, releasing, ci verification (required), release notes and new: feature name (by @contributor).