forecasting_os

A set of project rules for a forecasting system: software that records predictions, links them to evidence, and measures how accurate they are. It describes a shared data structure, three user-facing areas, deterministic matching, and trace records of system steps.

In plain words
What is it for?
Use it when working on forecast creation, refreshing, resolution, evidence links, accuracy records, calibration charts, LinkedIn signal posts, and the system’s trace-audited workflows.
Why use it?
It gives developers a defined way to connect signals and evidence to forecasts and to track how each forecast update was produced.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/homenshum/nodebenchai/forecasting_os
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00992
Opus 5 $0.00000 $0.00496
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 2d ago against content hash eda2b05045e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forecasting_os 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.

.cursor/rules/forecasting_os.mdc · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forecasting OS

Architecture

Three surfaces, one data spine

  1. LinkedIn posts: Signals surface as Δ badges (Post 1), evidence→forecast links (Post 2), delta + trace breadcrumbs (Post 3)
  2. Dashboard (ForecastCockpit): CalibrationPlot, BrierTrendChart, ForecastCard with evidence timeline, TraceBreadcrumb
  3. MCP tools: 9 tools (create_forecast, refresh_forecast, resolve_forecast, get_forecast, list_forecasts, add_forecast_evidence, get_forecast_track_record, compute_calibration, create_forecast_from_signal)

Cross-reference engine (deterministic, no LLM)

  • signalMatcher.ts: keyword overlap (+1/token), entity match (+3), tag match (+2), driver match (+2). Threshold: score ≥ 3
  • Exports: matchSignalsToForecasts, matchFindingsToForecasts, formatDeltaBadge, formatEvidenceLink

TRACE wrapping

  • Every forecast refresh is TRACE-audited: 6 steps (query → fetch → match → score → update → complete)
  • Every LinkedIn post is TRACE-audited: 5 steps (digest → explanations → cross-ref → format → post)
  • workflowTag links steps across an execution (e.g. forecast_refresh_2026-02-15)

Key files

File Purpose
convex/domains/forecasting/forecastManager.ts CRUD + 6 public dashboard queries
convex/domains/forecasting/signalMatcher.ts Deterministic signal↔forecast cross-reference
convex/domains/forecasting/traceWrapper.ts TRACE-wrapped forecast refresh (6 audit steps)
convex/domains/forecasting/scoringEngine.ts Brier + log scoring, proper scoring rules
convex/domains/forecasting/schema.ts 5 tables: forecasts, forecastEvidence, forecastResolutions, forecastUpdateHistory, forecastCalibrationLog
convex/workflows/dailyLinkedInPost.ts LinkedIn pipeline with Δ badges, evidence links, TRACE
src/features/research/components/ForecastCockpit.tsx Dashboard assembler (CalibrationPlot, BrierTrendChart, ForecastCard)
packages/mcp-local/src/tools/forecastingTools.ts 9 MCP tools

Read the full file on GitHub · 60 lines

Changes

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.

  1. 2d ago First seen · 60 lines · 0 tokens per session scan A eda2b05045e7

Subscribe to this mod's changes

forecasting_os is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 992 tokens. 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.