Repo · Coding & code review
decision-first
Agent skill that spots bounded-judgment steps, tries TypeSafe Jev (Choice / Score / Noul) before regex/LLM heuristics, and documents every attempt in…
Open github.com ↗From the repository
Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt
agent-skillsai-agentsclaude-codecoding-agentsjevsystem-onetypesafe
How builders describe it
Agent skill that spots bounded-judgment steps, tries TypeSafe Jev (Choice / Score / Noul) before regex/LLM heuristics, and documents every attempt in a reusable “decision lab” directory.
Agent skill that pushes a coding agent to try Jev before it writes another regex or prompt, then writes down what happened. Four reference files, an eval set of 20 trigger prompts, and three stdlib Python scripts for running questions, scoring agreement against labels you already have, and keeping…
The decision Jev makes
Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.
Where it fits
Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →
Related projects
Coding & code reviewjevkit (bragamat)Unofficial jev CLI (Homebrew, Scoop, install script) that puts TypeSafe Jev in a coding agent's toolbox: find/check to read less, decide/yesno/score…GitHub · ★ 3 · bragamat
Coding & code reviewJevTraceMCP server that cuts coding-agent token usage by retrieving only the snippets TypeSafe Jev judges relevant.GitHub · ★ 3 · 123wwwa
Coding & code reviewBaton Agent OrchestratorIdea-to-reviewed-code pipeline on your git repo (jev CLI): TypeSafe Jev picks the agent, model and effort at each step across Claude Code, Codex CLI…GitHub · Gane2506
Coding & code reviewtern-chirpTiny robot voice for the Tern terminal: when a coding agent finishes or waits for you, Jev reads the end of its last message and answers six typed…GitHub · ★ 3 · Noctivoro
Coding & code reviewreasoning-routerPer-step reasoning effort for coding agents picked by a classifier (TypeSafe Jev by default in examples) without breaking the prompt cache; ships an…GitHub · ★ 2 · robertn702
Coding & code reviewjev-mswMock Jev API decisions with MSW for deterministic tests without real API calls or credits.GitHub · ★ 2 · royalpinto007