All Claude Code modsKilimcininKorOglu/claude-code-mods
gemini-plan-review
Has Gemini review each plan before the approval dialog, from the plan and the conversation, and sends a plan with a blocking finding back to the model, at most twice. Off until /gemini-plan-review on; gemini-core holds the key, tier, model and thinking level.
gemini-plan-review reaches L3 (network) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.
- Events hooked: 5
- API methods referenced: 15
- Access from classified calls: L3, network: network, reads files, reads the transcript, persists state, draws
- Unclassified calls: 4 (
$.gemini.enroll,$.gemini.read,$.gemini.request,$.gemini.settings), full access unknown - Static scan, not a runtime test
Install hint
/plugin install gemini-plan-review --marketplace KilimcininKorOglu/claude-code-modsFrom 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.
Access
L3 Uses the networkother: $.gemini.enroll, other: $.gemini.read, other: $.gemini.request, other: $.gemini.settings, network, reads files, reads the transcript, persists state, drawsValidation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- every prompt, ExitPlanMode calls
- Hooks
session.start, command.run {command=gemini-plan-review}, prompt.submit, prompt.attachment {type=plan_mode}, tool.call {tool=ExitPlanMode}- API calls
$.clock.now, $.clock.sleep, $.command.register, $.fs.read, $.gemini.enroll, $.gemini.read, $.gemini.request, $.gemini.settings, $.http.fetch, $.session.messages, $.store.delete, $.store.get, $.store.set, $.ui.log, $.ui.toast- Validation on 2.1.302
- Passed
- Scanned revision
887502f53795- Marketplace passed
- kilimcininkoroglu-mods
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 KilimcininKorOglu/claude-code-mods
- action-pinAfter an edit that adds a GitHub Actions step pinned to a tag or a branch, names the commit SHA to write inst…
- ask-autopickPicks the recommended option of a question that waited unanswered for a set time, so a session you left does…
- bash-dietShrinks each Bash result before the model reads it: per-command filters for git, test runners, linters, packa…
- bg-tasksShows the background shell tasks of the session on the status line or in the shared sidebar, with the oldest…
- bughuntRuns proof-driven bug hunt rounds with /bughunt: each round proves one bug with a failing command the mod run…
- cache-warmKeeps the 1-hour prompt cache warm for a window you set, or with no end in every session under always, with o…
- commit-cadenceNames the uncommitted files to you at the end of each turn, and tells the model at the next prompt to commit…
- config-parseParses each JSON, YAML, TOML or .env file an Edit or Write touches, notes a parse error at once instead of at…
- context-restoreHands a skill or command call the current text of its file when the file changed on disk after the session lo…
- contract-watchAfter the model changes a function signature with Edit, adds the callers ripwire finds to the Edit's result,…
- councilAsks a council of models about a hard problem, when the model calls its tool or you run /council <question>:…
- dep-sentinelChecks each package the model installs against its registry and OSV.dev, and stops a missing, brand-new, look…
- desk-notifySends a desktop notification when a question or a plan waits for your answer, and when a turn ends or fails.
- diagram-renderRenders the mermaid blocks of the model's replies with an installed mmdc after each turn and draws each pictu…
- disk-janitorMeasures the build artifacts of the repository, shows them on the status line from 5 GB, and deletes the ones…
- doc-drift-watchAfter each commit the model makes, adds the doc lines that commit made stale (file:line references, symbol na…
- edit-loopAdds a note to the fifth edit of one file in one turn, so the model re-reads the code path and states the roo…
- effort-autoHas a small model rate how hard each prompt is and runs that turn and its subagents at the matching effort, w…
- env-syncAfter each commit the model makes, names the env variables its added lines read that .env.example lacks, with…
- error-pokeSends one continue prompt after a turn an API error killed, so the half-done work carries on instead of the s…
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/KilimcininKorOglu--claude-code-mods--gemini-plan-review/)
[](https://mods.aidojo.si/mods/KilimcininKorOglu--claude-code-mods--gemini-plan-review/)