jeremylongshore

agent-governance-plane (AGP) — one-pager + operator-grade system analysis (v0.1.87; reviewed 2026-06-24)

agent-governance-plane (AGP) v0.1.87

Slack-native, OSS governance for AI coding agents: sandboxed execution, human-in-the-loop approval on every tool call, and a signed audit log of each.

A Slack-native, OSS-first governance plane that runs an agent harness (Claude Code and Codex) inside a Docker sandbox, gates every tool call through a policy engine and Slack human-in-the-loop approvals, and records each event in a signed, hash-chained audit journal you can verify offline. Apache-2.0, single-operator by default, fail-closed throughout. The agp CLI + governance kernel are a Bun + TypeScript codebase: ~117 source modules, 299 tests, one runtime dependency (zod).

AGP composes the production-shipped CCSC kernel (claude-code-slack-channel v0.10.0 — Slack relay, sandbox spawn, policy gate, hash-chained journal) rather than reinventing it. Compose, don't reinvent.

jeremylongshore

gastown-viewer-intent v0.6.0 — one-pager + operator audit

gastown-viewer-intent v0.6.0

Local-first Mission Control dashboard for Beads + Gas Town, with a read-only-forever memory panel.

A single Go daemon + embedded React UI that surfaces bd (issue tracker) and gt (multi-agent orchestrator) state in one browser tab — so the engineer doesn't alt-tab to a terminal every two minutes to run bd ready or bd dolt status. Loopback bind enforced, Origin-allowlist gated, memory content classification-redacted by default.

jeremylongshore

Bundled-host architectural sketch — Kobiton Automate plugin

Author: Jeremy Longshore (Intent Solutions) Date: 2026-05-18 Reference: kobiton/automate#53 — mimosa767's "Reduce Claude Dependency Friction" ask, specifically Ask 6 (future product direction) Status: DRAFT — decision-support sketch, not a roadmap Related: Architectural one-pager mapping each #53 ask to L1 / L2 / L3 layer · README compatibility matrix

---

jeremylongshore

Guidewire MCP for Claude

Carrier-native MCP server for the Guidewire InsuranceSuite. Ask Claude underwriter / claims / billing questions in operator vocabulary; the harness gates writes.

Links:

jeremylongshore

plugins-nixtla v1.10.0 — One-Pager + Operator Audit

Claude Code plugins and AI skills for time-series forecasting with Nixtla

Version: 1.10.0 | Plugins: 19 | Skills: 30 | License: MIT

Links: GitHub · Nixtla SDK · TimeGPT

---

jeremylongshore

Blog Content Pipeline — Quick Reference

Reference card for the 4-tier content classification system, 4 skills, and 3 agents that power startaitools.com publishing.

Version: 3.0.0 | Author: Jeremy Longshore | Last Updated: 2026-04-09

---

The 4-Tier System

jeremylongshore

bobs-big-brain-compiler — Local-first knowledge OS (One-Pager + Operator Audit)

bobs-big-brain-compiler v1.22.0

Formerly intentional-cognition-os — renamed 2026-07-19; the npm package keeps that name.

Compile knowledge for the machine. Distill understanding for the human.

A local-first knowledge operating system that ingests raw source material, compiles it into structured semantic knowledge, creates scoped research workspaces for hard questions, and generates durable artifacts. The key insight: compilation, not indexing. The deterministic control plane owns all state; the AI proposes, the system decides.

jeremylongshore

Malouf Furniture — How It All Connects

For Gardner — This is the big picture of what we're building. Your existing tools feed into one central database, an AI brain reads that database, and your team gets the answers and automations they need without changing how they work day to day.

Nothing below is set in stone — this is the direction based on our conversation. The discovery form will fill in the blanks.

---

The Architecture

jeremylongshore

j-rig-skill-binary-eval

Software-grade release discipline for Claude Skills

Seven-layer binary evaluation harness that treats SKILL.md artifacts as production software. Package integrity, trigger precision, functional quality, regression gating, baseline comparison, model-aware testing, and evidence-backed rollout decisions — all through binary yes/no criteria with external evaluators. The evidence surface emits the kernel-normative gate-result/v1 predicate from @intentsolutions/core, and the fail-closed decision logic ships as the published npm package @intentsolutions/rollout-gate.

[](https://www.npmjs.com/package/@in

jeremylongshore

x-bug-triage-plugin v0.4.1

Closed-loop bug triage pipeline that turns public X/Twitter complaints into filed GitHub issues with human confirmation at every step.

X complaints hit your product every day. Most teams discover them by accident — days or weeks later. This plugin ingests complaints from X/Twitter, normalizes them into structured bug candidates, clusters by family, scans repos for evidence, routes to owners, displays interactive triage results in the terminal, and files GitHub issues only after explicit human confirmation.

Links: GitHub · GitHub Pages