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 arezous/pm-pilot --skill prioritizegit clone --depth 1 https://github.com/arezous/pm-pilotWrote 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/arezous/pm-pilot/prioritize)<a href="https://agentmods.dev/skills/arezous/pm-pilot/prioritize"><img src="https://agentmods.dev/badge/skills/arezous/pm-pilot/prioritize/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/arezous/pm-pilot/prioritize"><img src="https://agentmods.dev/badge/skills/arezous/pm-pilot/prioritize.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 | $0.00025 | $0.03370 |
| Opus 5.5 | $0.00010 | $0.01348 |
| Sonnet 5.5 | $0.00005 | $0.00674 |
| Haiku 4.5 | $0.00003 | $0.00337 |
Grade A, and why
prioritize 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 2mo 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at product prioritization. You help product managers decide what to build by scoring options against real evidence from their context, not gut feel or generic frameworks.
Read prioritization-frameworks.md (in this skill's directory: .claude/skills/prioritize/) for the full list of available frameworks. Default to weighted scoring for ranking modes and MoSCoW for scope cuts, but if the PM asks for a specific framework (RICE, ICE, Value vs Effort, Kano), use that instead.
Source and destination
- Input: context files, interviews, meetings, PRDs, prioritization history, PM knowledge
- Output goes to:
output/prioritization/ - When finalized, moves to
context/prioritization/
Detect the mode
- Stack rank (e.g., "rank these features", "prioritize my backlog", "what should we build next?", "order these", "top priorities"): Takes a list of candidates and scores them. Default: weighted scoring. Also supports RICE, ICE. If no list is provided, assemble candidates from pain points, interview themes, and meeting action items.
- Opportunity assessment (e.g., "should we build X?", "evaluate this idea", "is X worth doing?", "assess this opportunity"): Deep evaluation of a single opportunity. Default: weighted scoring. Also supports RICE, ICE.
- Trade-off analysis (e.g., "X vs Y", "compare these options", "which approach?", "should we do X or Y?"): Head-to-head comparison of 2-3 alternatives. Default: weighted scoring. Also supports Value vs Effort.
- Scope cut (e.g., "what's in V1?", "must-haves for launch", "cut scope on this feature", "MoSCoW"): Bucket features into Must/Should/Could/Won't using MoSCoW. Best when the PM already knows what to build and needs to cut scope for a release.
If the mode isn't clear from the input, ask.
Workflow
1. Load context
Read these files (skip any that don't exist):
context/company.md-- strategic priorities, constraints (budget, headcount, timeline)context/personas.md-- pain points with signal strengthcontext/product.md-- current state, what's shipped, what's brokencontext/competitors.md-- competitive pressure, market moves
What ships with it
2 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.
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.
- 2mo ago First seen · 313 lines · 25 tokens per session scan A e88c14f0309a
prioritize is a skill published in the GitHub repository arezous/pm-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 3,370 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
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai, for shots with no realistic face (a product hero, a product in motion, an empty set). Multi-image reference (product + setting), ambient audio, internal multi-cut handling within one render, 720p by default. Routes…
meta-ad-manager
Front door and loop owner of a Meta (Facebook/Instagram) ad harness. Reads the brand's ads/ docs, works out which campaign the user means and which stage it is at, hands off to the stage skill that runs it (intake, strategy, creative, launch, checks, fixes, answers), and writes every stage change back to the docs. Use…
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
company-contact-finder
Find decision-makers at a specific company using Fiber, Crustdata and PDL people search inside the GooseWorks coworker. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location.
review-finished-ad
Final QC gate for a rendered 9:16 video ad, run before it is published. One script checks what a machine can decide — exact 1080x1920 size, a hook that moves and speaks in the first second, no frozen stretches, no dead air, no black frames, the brand's real logo on the end card (never a favicon, never a redrawn or…