Repo · Coding & code review
Reticle
An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts…
Open github.com ↗From the repository
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
agent-skillagent-skillsagent-testingagent-verificationai-testing-toolautomated-testingclaude-codeclaude-skillshacktoberfestjevplaywright-mcpproof-layerreticle-mcpskills-shtesting-tool
How builders describe it
An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts with the file:line to fix; its listing frames the approach as Jev-style machine-native runtime perception.
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 239 coding & code review projects →
Related projects
Coding & code reviewjevlang (RoyWiggins)Python codec preprocessor: if/while/match conditions decided by TypeSafe Jev (including English conditions); upstream LICENSE file missing.GitHub · ★ 1 · RoyWiggins
Coding & code reviewjev-req-gateQuality gate for AI-generated requirements: TypeSafe Jev MECE questions route PASS/REVIEW/BLOCK with calibrated probabilities.GitHub · thomaszta
Coding & code reviewQuicksilverClaude Code skill that hands bulk judgment and shortlist calls to TypeSafe Jev so Claude spends tokens on harder reasoning.GitHub · ★ 52 · UditAkhourii
Coding & code reviewClaude x JevClaude Code skill and slash commands that use TypeSafe Jev (via OpenRouter) to classify, route, and gate so Claude deep-reads only the unsure items.GitHub · ★ 10 · charlesdove977
Coding & code reviewjev-test-impactTest impact analysis: Git diff and static dependency filtering produce candidates; TypeSafe Jev scores which Vitest/Jest files to run, with a…GitHub · ★ 2 · holasoymalva
Coding & code reviewadeciderTyped System One decisions for coding agents: one call sends state plus many Noul/Choice/Score questions and returns calibrated answers; backends are…GitHub · ★ 1 · Agents365-ai