Self-hosted, auditable email triage for Claude — Gmail and Outlook, with real actions.
IntentMail is a single-repo, self-hosted MCP server (+ CLI/TUI, Discord bot, and web dashboard) that gives an AI assistant a full grip on your inbox: daily-digest triage with priority and "why", long-thread summaries, group-by-category, and actual write actions (archive / flag / move / draft / delete) across Gmail and Microsoft Graph — while you hold the OAuth token and the mailbox never leaves your machine.
How the cost-leak hunter actually works under the hood: the filesystem, the data model it reads, the SQL primitive, the four detectors, and the deterministic ranker — exposed.
| Skill | databricks-cost-leak-hunter |
| Version | 0.1.0 |
| Author | Jeremy Longshore <jeremy@intentsolutions.io> |
| License | MIT |
Make AI-assisted open-source contributions land cleanly — caught by deterministic gates before they reach maintainers as slop.
A local-only Claude Code skill plus workspace for contributing to open-source projects you don't own. It runs 51 deterministic safety gates over every claim comment, design issue, and pull request, so AI-generated work never reaches an upstream maintainer as low-quality "slop." State is plain markdown — greppable, git-trackable, no database, no cloud calls.
Links: GitHub · Latest release
Deterministic test-enforcement toolkit — hash-pinned policy, escape-scan refusal gates, CRAP scoring, architecture checks, and signed evidence emission, installed in the repo it governs.
A zero-runtime-dependency CLI (Node dispatcher + bash/Python scripts) that makes test-quality policy enforceable on fresh clones. Companion to the audit-tests and implement-tests Claude Code skills, and the deterministic-gates layer of the Intent Eval Platform — but usable standalone in any repo.
The canonical contracts kernel for the Intent Eval Platform — types, schemas, and validators with no runtime attached.
TypeScript types, JSON Schemas (draft 2020-12), generated Zod validators, and state machines for the platform's 13 canonical runtime entities, the NORMATIVE gate-result/v1 in-toto predicate, and the bicameral authoring-contract families (authoring/v1, byte-frozen, plus the strict authoring/v2 skill-frontmatter fork). Every validator in the platform — deterministic gates, behavioral evaluators, the rollout-gate decision shell — imports its contract definitions from this one package.
The methodology and specs home of the Intent Eval Platform — where spec authority is kept provably in sync with upstream truth.
A research umbrella for vendor-neutral evaluation methodology around AI plugins, agents, MCP servers, and skill-discovery systems. The repo ships no application code: its outputs are versioned spec modules, normative blueprints, a decision-record governance corpus, and a continuous spec-compliance watcher that monitors 16 upstream spec surfaces daily and feeds the canonical contracts kernel (@intentsolutions/core).
Links:
A GitHub Action that consumes signed Evidence Bundles and decides allow / block for your CI pipeline — fail closed, zero decision logic in the action itself.
intent-rollout-gate is the GitHub Action shell layer of the Intent Eval Platform. It reads an Evidence Bundle (in-toto Statement v1 rows under predicateType https://evals.intentsolutions.io/gate-result/v1), resolves a declared rollout policy, and emits an allow or block decision with full reasoning. Every line of decision logic is delegated to the published @intentsolutions/rollout-gate package (Apache-2.0, sigstore provenance) — the action only wires inputs, files, outputs, and exit codes around it. v0.1.0 (the M5 TypeScript MVP) released 2026-06-12. Status: v0.1.0-experimental — behavior is real and fail-closed, but the consumption contract is not yet frozen (see graduation criteria be
Live demo: https://demos.intentsolutions.io/databricks-cost-leak-hunter/
That's ~$324K/year. The $100K/month spend is the only assumed input; the 27% waste rate is published.¹ Every line below is one config change.
| # | Where it's leaking | $/month | The fix |
agent-governance-plane (AGP) — one-pager + operator-grade system analysis (v0.1.87; reviewed 2026-06-24)
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.
gastown-viewer-intent v0.6.0 — one-pager + operator audit
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.
