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 divinevideo/divine-mobile --skill montecarlo-subgroup-predictiongit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/montecarlo-subgroup-prediction)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/montecarlo-subgroup-prediction"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/montecarlo-subgroup-prediction/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/divinevideo/divine-mobile/montecarlo-subgroup-prediction"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/montecarlo-subgroup-prediction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.01416 |
| Opus 5.5 | $0.00055 | $0.00566 |
| Sonnet 5.5 | $0.00027 | $0.00283 |
| Haiku 4.5 | $0.00014 | $0.00142 |
Grade A, and why
montecarlo-subgroup-prediction 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monte Carlo Sub-Group Prediction Scaling
Problem
When running Monte Carlo simulations for project completion, predicting dates for sub-groups (milestones, priorities, epics) within a larger project produces identical results for all groups, or simulations diverge and hit the max_weeks cap.
Context / Trigger Conditions
- Building a project forecasting tool that predicts dates for individual milestones or priority groups within a larger project backlog
- All sub-group predictions show the same date despite very different remaining counts (e.g., 5-item milestone shows same date as 46-item milestone)
- Simulations hit max_weeks (104) and produce dates 2+ years in the future
- Scope rate applied per-group causes negative net velocity (items grow each week)
Root Causes
1. Proportional Scaling is Mathematically Constant
If you scale throughput proportionally:
share = remaining_i / total_remaining
scaled_throughput = overall_throughput * share
weeks = remaining_i / scaled_throughput
= remaining_i / (overall_throughput * remaining_i / total_remaining)
= total_remaining / overall_throughput # CONSTANT for all groups!
Every sub-group predicts the same number of weeks regardless of size.
2. Overall Scope Rate Overwhelms Sub-Group Throughput
If the project's overall scope rate is 50 items/week and you apply it to a sub-group with only 5 remaining items (share = 1.6%), the scaled throughput might be ~0.6/week while scaled scope is ~0.8/week. Net velocity is negative — the simulation never converges and hits max_weeks.
3. GitHub created_at ≠ "Added to Board"
Scope rate calculated from created_at dates reflects when GitHub issues were created,
not when they were added to the project board. Bulk triaging or importing old issues
inflates the apparent scope rate dramatically.
Solution
Use different simulation models for different sub-group types:
For Sequential Priorities (P0, P1, P2...): Cumulative Model
Higher priorities are completed first. Each priority's prediction includes all higher-priority work that must finish before it:
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 · 155 lines · 137 tokens per session scan A b67e9992983a
montecarlo-subgroup-prediction is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 137 tokens to every session and 1,416 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…