alex-jb

8 mods across 5 repositories, 16 stars between them.

sfos-splunk-obs

01

alex-jb/solo-founder-os

Skill Claude CodeCodex

Ship reflections, eval drift, and bandit regret from the solo-founder-os 11-agent stack into Splunk over HEC. Five-minute install, zero new Python deps (stdlib urllib + json + sqlite3), six-panel dashboard you import once. Use when the user runs solo-founder-os agents on cron / launchd and asks "are my agents learning…

11 1mo ago A 136 tokens original MIT

adversarial-debate

02

alex-jb/claude-debate

Skill Claude CodeCodex

Run an Advocate/Critic/Judge debate over any decision with real tradeoffs. Use when the user asks whether to merge a PR, pick an architecture, hire a candidate, ship a feature, or make any judgment where both sides have valid points and a single-model answer would be too confident.

2 4mo ago A 65 tokens original MIT

build-quality-agent

03

alex-jb/build-quality-agent

MCP server Claude CodeCodexCursor

Claude-powered git pre-push diff reviewer for indie OSS projects. Runs locally from the build-quality-agent Python package.

1 2mo ago A tokens not measured original MIT

alex-jb/shadow-perception-mcp

Skill Claude CodeCodex

Pre-submit council for Kaggle notebooks. Five voices review the notebook for train/test leakage, protected-class proxy features, seed pinning, competition rule compliance, and submission artifact presence. Returns SHIP / REWORK / BLOCK verdict with per-voice rationale and Ed25519 attestation. Use before hitting Submit…

0 1mo ago A 74 tokens original MIT

alex-jb/shadow-perception-mcp

Skill Claude CodeCodex

Pre-publish council for Power BI Tabular models. Five voices review .bim / .tmdl / .dax for divide-by-zero without DIVIDE(), USERPRINCIPALNAME() bypassable without an RLS role, duplicate measure names, PII column references, and performance smells (nested CALCULATE, EARLIER pattern). Returns SHIP / REWORK / BLOCK…

0 1mo ago A 108 tokens original MIT

alex-jb/shadow-perception-mcp

Skill Claude CodeCodex

Pre-publish council for R data-science analyses. Five voices review a .R / .Rmd / .qmd file for reproducibility (seed / renv / sessionInfo), fairness (ECOA §701 / GDPR Art. 9 protected classes), statistical rigor (p-hacking / multiple comparisons without p.adjust), data provenance (local vs remote sources), and output…

0 1mo ago A 116 tokens original MIT

alex-jb/shadow-perception-mcp

Skill Claude CodeCodex

Pre-submit council for trading tickets. Five voices review a JSON trade ticket for Kelly-cap compliance, missing stop-loss, sector or single-name concentration limits, fat-finger qty (10× typical = BLOCK, Knight Capital 2012 lesson), and Reg BI Care Obligation on retirement accounts. Returns SHIP / REWORK / BLOCK…

0 1mo ago A 99 tokens original MIT

alex-jb/shadow-perception-mcp

MCP server Claude CodeCodexCursor +2

MCP server "shadow-perception-mcp" as configured in alex-jb/shadow-perception-mcp. Runs locally from the shadow-perception-mcp npm package.

0 1mo ago A tokens not measured original MIT