factor-report

A reporting and export workflow for completed FactorMiner research. It creates Markdown or HTML reports, charts, and factor-library exports in JSON, CSV, or plain formula formats.

In plain words
What is it for?
Generating research notes, visualizing factor performance and correlations, and exporting factor libraries for further analysis or handoff.
Why use it?
Research results are harder to review or hand off when they remain in raw run files. This packages the findings, metrics, plots, and formulas into usable artifacts.

Skill for Claude CodeCodex

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 skills/minihellboy/factorminer/factor-report
Any agent
npx skills add minihellboy/factorminer --skill factor-report
Clone the repo
git clone --depth 1 https://github.com/minihellboy/factorminer

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 565 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 $0.00080 $0.00565
Opus 5 $0.00040 $0.00282
Sonnet 5 $0.00016 $0.00113
Haiku 4.5 $0.00008 $0.00056

Measured 2d ago against content hash 51d13aa01412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factor-report 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.

integrations/factor-researcher/plugin/skills/factor-report/SKILL.md · 58 lines

What it actually says

Factor Report

This skill turns a finished run into reviewable artifacts: a static report, plots, and portable exports.

Workflow

1. Static report

factorminer report output/run1/factor_library.json \
  --session-log output/run1/session_log.json \
  --format markdown --output output/run1/report.md
  • --formatmarkdown or html. HTML is self-contained (no JavaScript).
  • --session-log — includes run metadata (iterations, yield rate).
  • --benchmark path.json — fold in benchmark results; repeatable.

The report defines every admission metric inline, lists each factor with its formula and IC/ICIR/correlation, and warns on stale artifacts.

2. Plots

factorminer -o output/run1 visualize output/run1/factor_library.json \
  --data market_data.csv --period test \
  --correlation --ic-timeseries --quintile --format png

3. Export the library

factorminer export output/run1/factor_library.json --format formulas --output output/run1/formulas.txt

--format options: json (full library), csv (tabular metrics), formulas (plain formula list for handoff).

Assembling the research note

A complete note pairs the generated report with narrative the analyst can sign off on:

  1. Objective & data — universe, horizon, split boundaries, validation status.
  2. Method — loop used (Ralph/Helix), features enabled, iteration budget.
  3. Library — admitted factors with formulas and out-of-sample IC/ICIR.
  4. Composite — backtest result net of costs, with the decay caveat.
  5. Benchmark — comparison vs. baselines, if run.
  6. Limitations — overfit risk, capacity, what was not tested.

Guardrails

  • The report presents results; it does not certify them. Frame it as research staged for human review.
  • Quote out-of-sample metrics as the headline; never the in-sample number.
  • Cite the run directory so every figure is reproducible via factorminer session inspect.
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 · 58 lines · 80 tokens per session scan A 51d13aa01412

Subscribe to this mod's changes

factor-report is a skill published in the GitHub repository minihellboy/factorminer (105 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 565 once invoked, about $0.0004 per session on Opus 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.