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 aleksander-dytko/ai-pm-workspace --skill create-epicgit clone --depth 1 https://github.com/aleksander-dytko/ai-pm-workspaceWrote 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/aleksander-dytko/ai-pm-workspace/create-epic)<a href="https://agentmods.dev/skills/aleksander-dytko/ai-pm-workspace/create-epic"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/create-epic/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/aleksander-dytko/ai-pm-workspace/create-epic"><img src="https://agentmods.dev/badge/skills/aleksander-dytko/ai-pm-workspace/create-epic.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 | $0.00020 | $0.01252 |
| Opus 5.5 | $0.00008 | $0.00501 |
| Sonnet 5.5 | $0.00004 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
create-epic 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Epic
You help turn a raw product idea into a well-structured epic draft. The output follows templates/epic-template.md and lands in epics/ with stage: Explore.
Input
The user provides via $ARGUMENTS:
- A short prompt (e.g., "unified onboarding dashboard for CSMs"), OR
- A path to a raw idea note (e.g.,
samples/sample-epic-idea.md)
Workflow
1. Gather context
Read the raw idea. If $ARGUMENTS is a path, read that file. Otherwise use the prompt directly.
Read supporting context in parallel:
templates/epic-template.md- the target structuredocs/epic-lifecycle.md- the stage frameworkresearch/personas/- personas that might match the target userDashboard/people-profiles.md- any stakeholders mentionedLoose Notes/Work/andMeetings/- related prior discussions (search by keywords from the idea)Initiatives/- does this fit under an existing initiative?
2. Identify gaps in the idea
Before drafting, identify what's missing or unclear. Ask the user 3-5 focused questions in ONE AskUserQuestion round if any of these are unclear from the raw input:
- Target user: which persona does this serve? (Offer personas from
research/personas/as options.) - Primary metric: what measurable outcome should improve?
- Scope boundary: what is explicitly NOT in this epic?
- Initiative fit: does this belong under an existing initiative (show list from
Initiatives/) or does it stand alone? - Competitor check: has competitive research been done? (Offer
/competitive-researchif not.)
Skip questions where the raw idea already has a clear answer. Maximum one round.
3. Draft the epic
Use templates/epic-template.md as the structure. Fill what you can from the raw idea + answers:
Required sections (always fill):
- Value Proposition Statement - one crisp statement of the outcome.
- User Problem - 1-2 paragraphs from the customer's perspective. Frame from the "why", not the product's failure.
- User Stories - 3-6 stories at the "what" level (Explore phase). Add the "how" later.
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.
- 1mo ago First seen · 117 lines · 20 tokens per session scan A bd729894bfdf
create-epic is a skill published in the GitHub repository aleksander-dytko/ai-pm-workspace (34 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 1,252 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
meeting-notes
Estructura y formatea notas de reunión siguiendo las mejores prácticas de PM. Úsalo cuando te pidan crear notas de reunión, formatear notas de discusión, capturar elementos de acción, o documentar decisiones de cualquier tipo de reunión. Produce notas estructuradas con decisiones, elementos de acción (responsable +…
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
stakeholder-update
Crear actualizaciones ejecutivas concisas para stakeholders usando el framework BLUF (Bottom Line Up Front). Usa cuando te pidan escribir una actualización de estado, reporte de progreso, comunicación de proyecto o briefing ejecutivo para liderazgo o stakeholders. Produce una actualización encabezada por BLUF con…
technical-debt-register
Documenta y prioriza un backlog de deuda técnica con impacto empresarial, estimaciones de esfuerzo y estrategia de resolución. Úsalo cuando se te pida auditar deuda técnica, crear un registro de deuda, priorizar deuda técnica para un trimestre, documentar atajos arquitectónicos o construir una hoja de ruta de…
cs-health-scorecard
Construir un cuadro de mando de salud del cliente para una cuenta específica. Úsalo cuando te pidan calificar la salud de la cuenta, evaluar el riesgo de renovación, construir un panel de salud o evaluar la probabilidad de que una cuenta se renueve o expanda. Produce un cuadro de mando de salud estructurado con estado…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…