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 superpmgit 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/superpm)<a href="https://agentmods.dev/skills/cskwork/oh-my-symphony/superpm"><img src="https://agentmods.dev/badge/skills/cskwork/oh-my-symphony/superpm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cskwork/oh-my-symphony/superpm"><img src="https://agentmods.dev/badge/skills/cskwork/oh-my-symphony/superpm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.02364 |
| Opus 5.5 | $0.00022 | $0.00946 |
| Sonnet 5.5 | $0.00011 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
superpm 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/superpm - one PM request, a verified artifact
One PM ask -> capture intent -> diverge by domain -> the smallest useful artifact -> an independent critic checks it against the framework and the real decision -> stop.
68 PM frameworks live in reference/; this file routes the ask and names the loop. For a
one-paragraph note you could write directly, skip the skill.
Principles
- Serve the real decision. Name the decision the artifact drives before drafting; a framework filled in for its own sake is waste.
- Smallest useful artifact. Only the frameworks the decision needs - no bolted-on SWOT/persona/roadmap when the ask was one pricing call.
- Ground claims in evidence. Numbers, quotes, segments come from the user's data, docs, or
named assumptions - never invented. Market/customer claims: pull real signal via
reference/signal.md(read-only, keyless) before asserting. - Surface hidden assumptions. The critic names unstated assumptions and missing pieces as risks - never present an assumption as fact.
- Ask only when genuinely ambiguous. Read the repo/docs/data first; interview only
load-bearing, user-only choices (
reference/intent.md). - Hard stops. Irreversible or outward-facing actions (publish, send, post, share externally) need explicit consent.
- Trace the chain. EXECUTE -> FLOW -> STORYBOARD -> PACKAGE share the 기능명세 (SPEC) as one
source of truth (
reference/model.md); a flow node or screen callout with no SPEC is never invented. Derived artifacts come from the spec, not beside it.
Intent capture - signal to domain
Read the request and route to one domain (the artifact named usually decides it). When the ask
spans domains, pick the primary deliverable and pull supporting frameworks from the others. When
the ask is to plan a buildable thing end-to-end (기획하자 / 개발하고 싶어, no single artifact
named), route to PLAN - a stepped session over the chain, not one artifact (reference/plan.md).
| Signal in the request | Domain | Reference |
|---|---|---|
| 기획하자 / 이거 개발하고 싶어 / 기획 도와줘 / plan this feature end-to-end / PRD부터 화면까지 | PLAN (session) | reference/plan.md |
| brainstorm ideas / risky assumptions / opportunity tree / prioritize features / customer interview / metrics | DISCOVER | reference/discover.md |
| product strategy / vision / value proposition / lean or business model / monetization / pricing / SWOT / PESTLE / Porter / Ansoff | STRATEGY | reference/strategy.md |
| PRD / OKRs / roadmap / sprint plan / retro / pre-mortem / user or job stories / stakeholder map / prioritization framework / red-team a plan | EXECUTE | reference/execute.md |
| user flow / 유저플로우 / flowchart / screen-to-screen flow / 화면 흐름 / 분기·상태 전이 | FLOW | reference/flow.md |
| 화면설계서 / 기능명세 / 스토리보드 / screen design doc / screen spec / wireframe / UI spec | STORYBOARD | reference/storyboard.md |
| implementation package / 구현 패키지 / 통합 산출물 번들 / export bundle / hand off to devs | PACKAGE | reference/package.md |
| personas / segments / customer journey / market sizing (TAM/SAM/SOM) / competitor analysis / sentiment | RESEARCH | reference/research.md |
| SQL from a question / cohort analysis / A/B test read-out | ANALYTICS | reference/analytics.md |
| go-to-market / beachhead / ICP / growth loops / GTM motion / battlecard | GTM | reference/gtm.md |
| marketing ideas / positioning / value-prop statements / product name / North Star metric | GROWTH | reference/growth.md |
| review or tailor a resume / draft an NDA or privacy policy / proofread | TOOLKIT | reference/toolkit.md |
| document an AI-built app / shipping artifacts / intended-vs-implemented gap | AI-SHIP | reference/ai-ship.md |
What ships with it
28 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.
- LICENSE 1.0 KB
- reference/ai-ship.md 2.4 KB
- reference/analytics.md 2.5 KB
- reference/critic.md 4.3 KB
- reference/discover.md 6.8 KB
- reference/execute.md 4.9 KB
- reference/flow.md 4.2 KB
- reference/growth.md 2.3 KB
- reference/gtm.md 2.7 KB
- reference/intent.md 4.6 KB
- reference/model.md 5.5 KB
- reference/package.md 2.9 KB
- reference/plan.md 3.6 KB
- reference/research.md 3.6 KB
- reference/signal.md 5.1 KB
- reference/storyboard.md 9.8 KB
- reference/strategy.md 3.8 KB
- reference/toolkit.md 2.2 KB
- scripts/shoot.sh 1.6 KB runs code
- templates/battlecard.md 898 B
- templates/opportunity-solution-tree.md 1.0 KB
- templates/prd.md 1.3 KB
- templates/storyboard-board.html 5.2 KB
- templates/storyboard-page.html 27 KB
- templates/strategy-canvas.md 1016 B
- templates/workspace-data-common.js 2.6 KB runs code
- templates/workspace-data-module.js 2.8 KB runs code
- templates/workspace.html 52 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.
- 2d ago First seen · 131 lines · 54 tokens per session scan A 090b66b3f89b
superpm is a skill published in the GitHub repository cskwork/oh-my-symphony (35 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 2,364 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
kagan
Read a ticket, link threads, and move work through the native Kagan board when the user asks for ticket work.
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.
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.
agtx-oneshot
One-shot a whole project on an agtx board: decompose the goal, run every task unattended, unblock the workers, and merge each one. Use when the user wants a long autonomous run rather than a single session.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.