Umby's Jev Stack

September 20, 2026 · View on GitHub

A skill tree of TypeSafe Jev agent skills over HTTP. Install the whole tree or grab one skill.

Repo: https://github.com/Umbylicus/umby-jev-stack · Tree index: TREE.md

Quick start (4 steps)

  1. Get a keyconsole.typesafe.ai → create a TypeSafe API key.
  2. Install — whole tree or one skill (see Install).
  3. Set JEV_API_KEY — exact name, case-sensitive.
  4. Prompt your agent — e.g. "Run umby-jev-review on this repo. Use frozen questions. Compile every finding."

Skill tree (11 skills)

#SkillUse when
1umby-jev-reviewFull repo review — six independent Nouls, executable defects only (v2.0.2)
2umby-jev-diff-gateSame hunts on git diff / PR patch only
3umby-jev-secretsStricter secret + PII sweep
4umby-jev-breaking-changeAPI / schema / export breaks
5umby-jev-test-gapBehavior change without tests
6umby-jev-agent-safetyDestructive command risk before run
7umby-jev-prompt-screenJailbreak / injection in user text
8umby-jev-issue-triageIssue type + urgency + independent security Noul
9umby-jev-docs-driftDocs claims to verify later
10umby-jev-browserBrowser Harness/Chrome — indexed operation/target heads + independent error Nouls
11Speedy JevIncremental clutter/performance candidates; ≥ 0.70 list; look-only proposals

See TREE.md for install details and how to add skill 12+.

Install

Whole tree

npx plugins add Umbylicus/umby-jev-stack --target cursor

Select umby-jev-stack. Works with --target claude-code or --target codex.

One skill

Same command — select the skill name when prompted (e.g. umby-jev-secrets).

Manual: cp -r skills/<skill-id>/ ~/.cursor/skills/<skill-id>/

API key (JEV_API_KEY)

WhereHow
Shellexport JEV_API_KEY="your-key"
Cursor desktopSettings → MCP/plugin env, or launchctl setenv JEV_API_KEY "$JEV_API_KEY" + quit/reopen from Dock
Cursor cloud agentsRuntime Secret named exactly JEV_API_KEY

Verify: test -n "$JEV_API_KEY" && echo okdo not commit keys.

How every skill works

  • HTTP-firstPOST https://api.typesafe.ai/v1/systemone, model jev-latest
  • Independent Nouls (or separate Choice + Score where documented) — every positive flag gets a compile row
  • Never a single highest-priority Choice that hides co-occurring hits
  • Jev classifies only; confirm/compile agents are look-only and explain possible remedies without editing application code. A human reviews and decides.

jev-review MCP is optional — not required.

License

MIT — see LICENSE.

Tree 1.6.0

  • Speedy Jev 1.0.0 adds a local candidate index (path/hash/kind/last-seen), incremental scoring, and four independent Nouls. Only Speedy lists scores ≥ 0.70.
  • Browser 2.0.0 follows jev-ultrafast: operation plus compatible speculative target heads in one request; text helper only for TYPE_TEXT; every error Noul ≥ 0.5 and click/type path are compiled.
  • Diff-gate 2.0.0 ports review v2 structured hunts and ignore lists, scoped strictly to diff/PR changes.
  • Review 2.0.2 clarifies look-only confirmation and the oversized-function chunk cap; Fable's six questions remain byte-for-byte unchanged. state.content ≤ 10,000 characters, repo-sized keep-alive HTTPS pool (concurrency = snippets), retry/backoff only as needed, and compile ≥ 0.5 remain intact.
  • Siblings use structured instructions/criteria and explicit evidence boundaries. Issue-triage 2.0.0 corrects Score criteria to an ordered array and retains security independently of category.

All skills use POST https://api.typesafe.ai/v1/systemone, model jev-latest, and JEV_API_KEY (SDK examples may use TYPESAFE_API_KEY). No application fixes or automatic cleanup. MIT; owner Billy Lewis / Umbylicus.