All Claude Code modsmako-code/gobworks
jev
Jev (TypeSafe's System One model) as Claude's instant co-processor: bulk filter/classify/rank/semantic-grep tools, risk notes under permission dialogs, a check on unverified 'it passes' claims, and optional per-prompt effort.
review UI rewrite
In its last recorded footprint, jev reaches L3 (network) by its classified calls and passed claude plugin validate on Claude Code 2.1.296.
- Events hooked: 9
- API methods referenced: 18
- Access from classified calls: L3, network: network, drives Claude, reads files, reads env vars, draws
- Unclassified calls: 3 (
$.state.get,$.state.set,$.tool.check), full access unknown - Last recorded footprint, revision
ec6ea23: Repository could not be scanned; showing the last known footprint. - Static scan, not a runtime test
Install hint
/plugin install jev --marketplace mako-code/gobworksFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later. The latest scan could not confirm this mod, so the command may be out of date.
Access
L3 Uses the networkother: $.state.get, other: $.state.set, other: $.tool.check, network, drives Claude, reads files, reads env vars, drawsValidation
not verifiedView the source on GitHub Back to the list
What the scan recorded
- Observed events
- mcp__jev__jev_filter calls, mcp__jev__jev_classify calls, mcp__jev__jev_rank calls, mcp__jev__jev_lines calls, mcp__jev__jev_ask calls, Bash|PowerShell calls, Edit|Write|NotebookEdit calls, every prompt
- Hooks
session.start, tool.call {tool=mcp__jev__jev_filter}, tool.call {tool=mcp__jev__jev_classify}, tool.call {tool=mcp__jev__jev_rank}, tool.call {tool=mcp__jev__jev_lines}, tool.call {tool=mcp__jev__jev_ask}, tool.call {tool=Bash|PowerShell}, tool.call {tool=Edit|Write|NotebookEdit}, prompt.submit, turn.start, turn.step, turn.complete, session.end, ui.render {component=AbovePrompt}, command.run {command=jev}, ui.render {component=Pane, requestId=jev}- API calls
$.clock.after, $.clock.now, $.clock.sleep, $.command.register, $.env.get, $.fs.read, $.http.fetch, $.prompt.submit, $.state.get, $.state.set, $.tool.check, $.tool.register, $.ui.close, $.ui.log, $.ui.notice, $.ui.open, $.ui.resolve, $.ui.toast- Validation on 2.1.296
- not verified
- Last known result
- Passed on 2.1.296
- Validator output
- Repository could not be scanned; showing the last known footprint.
- Scanned revision
ec6ea2383749- Marketplace passed
- gobworks
- UI rewrite review
- UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. mods/jev/jev/hooks/jev-format.ts:505
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
More from mako-code/gobworks
- achievementsA little game layer: 32 achievements for how you use Claude Code, with lifetime progress and a /achievements…
- agent-routerPicks the model for each subagent by its type (Explore on Haiku by default) and can cap how many run at once.
- arcadeSomething to do during long turns: /snake and /2048 in a pane, with high scores and a nudge when Claude is do…
- attributionYour commit and pull request credit line, your way: Claude Code's default, none, or your own template with {m…
- auto-contextSay "this error", "the tests", "this file", "what you just did" or "the plan" and what it points at goes alon…
- auto-continueKeeps work flowing: when Claude stops mid-task ("Next I'll…") or asks an obvious yes ("Shall I continue?"), a…
- auto-polishEvery prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the g…
- auto-retryKeeps long sessions going through API errors and rate limits: resubmits after a backoff when idle, waits out…
- auto-reviewA quick second pair of eyes after edits: reviews the turn's diff in the background and offers to fix what it…
- autotunePer-prompt effort autopilot: classifies each prompt (Jev, Claude Haiku, or heuristics) and sets that turn's e…
- bash-guardBlocks catastrophic shell commands (rm -rf ~, curl | sh, force-push to main, DROP DATABASE, format C:) and as…
- benchMeasures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved b…
- best-of-nRuns 2-4 attempts at a task in parallel git worktrees, each with a different approach; compare their diffs an…
- bisectFinds the commit that broke something: git bisect with your test command in a temporary worktree (your workin…
- branch-guardKeeps work off protected branches: no commit, merge, rebase, cherry-pick, am or push on main/master/release/*…
- cache-guardAsks before /model, /output-style, /fast, /effort, MCP or plugin changes and /config rows that would throw aw…
- cache-lensPrompt-cache hit rate, a live warm/cold countdown, cache-bust alerts with likely causes, savings, and optiona…
- canvasGives Claude a screen to draw on: SVG diagrams and Markdown reports in a Canvas pane with history.
- ci-autopilotCI that fixes itself with your say-so: watches the branch's workflow run after a push, puts a failure with it…
- clarifierAsk before guessing: when a prompt looks ambiguous, Claude asks up to three clarifying questions first. Off u…
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/mako-code--gobworks--jev/)
[](https://mods.aidojo.si/mods/mako-code--gobworks--jev/)