ClaudeCodeMod

All shelves / Mods / Review

done-gate

By vumichien

done-gate is a Claude Code review mod by vumichien.

Tells Claude and you, in a toast, when a task is marked done while changed code is untested, and draws the last test run in a band.

Draws

Install

The marketplace name is chien-mods.

In your shell
claude plugin marketplace add vumichien/claude-code-mods-kit
claude plugin install done-gate@chien-mods
Open the repo

It runs inside the Claude Code process. The side panel is only what the author's README names. Read the repo before you install, or run claude plugin validate on the plugin folder.

Version
0.3.0
License
MIT
Repo stars
4
Last change
2026-10-10

What it can reach

  • Draws in the session
  • Reads this turn's file edits
  • Sees tool calls

Start a new session after installing, then turn it on with /done-gate on; it starts off. Tested on Claude Code 2.1.296 on Windows 11; mods are an early-access feature, so the API can change between versions. The testCommands option adds commands that run your tests to the runners it already knows, and ignore lists file endings that need no test run. It warns and never blocks, it cannot tell whether your tests cover the changed files, since any passing test run counts, and it does not see files changed by a shell command or outside Claude Code, nor a test run sent to the background. It keeps its record for the session only. To try it for one session without installing, git clone the repository and start claude with --plugin-dir pointing at the mod's folder.

The marketplace, chien-mods, also holds secret-guard, plan-meter, context-meter, idea-shelf, session-monitor, prompt-enhancer, and assumption-check, each installed on its own. Catching a done claim that no test run backs is why this page files it under review. test-hud, by ice-lfernandes, draws each test run on the status line, passing over total with a sparkline of failures. redgreen opens a Tests pane when a test run Claude starts fails, with each failure's assertion and diff. This one does not run your tests: it watches the files Claude edits and the test commands Claude runs, and when a task is marked done, through TaskUpdate or TodoWrite, with changed files unchecked, Claude reads a note beside that tool's result and you get the same text as a toast. A passing test run clears the files changed before it, and a failing one keeps them and turns the band red. When a pipe or a second command makes the exit status unreliable, it reads the runner's own summary line instead.

Demo

A list item of the What done-gate does section of the author's claude-code-mods-kit README: when Claude marks a task done through TaskUpdate or TodoWrite while changed files are unchecked, Claude reads a note beside the tool's result and you see the same as a toast, quoted as: done-gate: "Add the export" was marked done, but 1 code file was changed and no test has run in this session: src/export.py, then asking Claude to run the covering tests or say plainly they were not tested. The task and file are the author's.
Screenshot of the author's GitHub page.

What it hooks into

  • session.startWhen a session starts
  • command.runWhen you run its slash command/done-gate
  • tool.callAround a tool call, where it can hold one
  • ui.renderDraws into the sessionAbovePrompt

Read from the on() calls in its hook modules. Open its source under Files to check what each one does.

Slash commands 1

  • /done-gateShow the last test run and the code files changed since (/done-gate on or off switches the mod)

Files

The author's source, 3 files. They load when you open them.

Facts

Author
vumichien
Category
Review
Marketplace
chien-mods
Repo
vumichien/claude-code-mods-kit
Folder
plugins/done-gate
Version
0.3.0
License
MIT
Repo stars
4
Last change
2026-10-10
Language
TypeScript
Files
7

Other mods in Review

prompt-enhancervumichienDraws an Enhance button above the prompt: Haiku rewrites your draft to name fitting skills, what to ask first, and what done looks like. It never sends it.assumption-checkvumichienLists the choices Claude made that you did not state after a turn that edited files or ran commands; mark each right or wrong and send the corrections.replay-theaterAnthropicAdds /replay. Steps through the files Claude edited last turn, one diff at a time.review-watchhamzaferDraws one line above the prompt per running code review, with the model, the target, the elapsed time, and Codex's latest output. A toast lists the findings.md-previewhamzaferWhen Claude edits Markdown, draws the before and after beside the session, rendered the way GitHub does.files-touchedSingh-APDraws one line above the prompt for files Claude changed this session, with lines added and removed. /touched pane lists them, and a press inserts @path.change-ledgerarasovicDraws a pane of every file this session touched, with lines added and removed and which agent edited it, beside the git working tree.turn-timelinearasovicDraws the current turn as a timeline: one lane for the main loop, one per subagent, the split between model, tools, and idle, and the three slowest steps.show-mearasovicDraws each mermaid diagram in an answer as a picture in a pane once the turn ends. /show-me asks for an answer in diagrams.image-peekarasovicDraws thumbnails of images you paste, above the prompt while you write, and larger pictures under the message once it is sent.plannotatorbacknotpropOpens Claude's plan in a review UI where you mark it up, sends your annotations back, and shows what changed when the plan comes back.filetreedata-goblinDraws an IDE-style file tree beside the transcript that lights up what Claude reads, writes, and commits, and follows it through the folders.
All 145 in Review