Menu
Rules for auto-dismissing code review findings that are false positives
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Activate when a user invokes /agentic-harness:precommit, :review, :submit, or asks to run a Prose-packaged review workflow ("precommit review", "run mr-review on MR 21", "submit MR 42 via prose", etc.). Verifies prereqs, resolves reviewer defaults, and delegates to the openprose skill which embodies the Prose VM for the actual program execution. Not for one-shot questions or static documentation lookups — decline unless the user clearly wants to run a pipeline.
Rules for deduplicating code review findings across agents
Local GitLab MR code review orchestrator. Use when the operator asks to "review this MR", "run a local MR review", "review my branch's MR", or wants a LOCAL-only (no GitLab posts) multi-dimensional review with automatic filtering and optional fix loop. Dispatches specialized review agents in parallel (intent, security, code quality, silent failures, type design, tests, comments), applies a 4-phase filtering pipeline, and iteratively fixes Critical/Important issues until convergence.
This skill should be used when the user asks to "address MR feedback", "fix review comments", "respond to code review", "handle MR suggestions", "shepherd an MR", "resolve discussion threads", or "run the MR feedback loop". Provides a systematic workflow for reviewing, implementing, and closing GitLab MR feedback — used standalone by operators AND as the thread-handling primitive for /agentic-harness:mr-submit.
Inspect and manage shepherd agents spawned by /agentic-harness:mr-submit. Use when the operator asks to "check MR status", "list active shepherds", "resume a shepherd after restart", "retire an MR", "approve drafted thread replies", or wants a dashboard of CI state and review-thread progress per MR. Reads state files under ~/.claude/mr-shepherds/; writes nothing except in response to an explicit mode flag.
End-to-end GitLab MR lifecycle orchestration. Use when the operator says "submit this MR", "open an MR with full review", "run the MR pipeline", "submit and shepherd", or wants to take a branch from "ready to push" through merge with automatic review, push, and CI/thread monitoring. Provides simplify → iterative review loop with TaskCreate-backed findings → push → open MR → background shepherd for CI + threads.
| name | false-positive-rules |
| description | Rules for auto-dismissing code review findings that are false positives |
Apply these rules to ALL findings. If a finding matches ANY rule, DISMISS it.
ANY finding about these variables -- they aren't attacker-controlled in CI context:
CI_* (CI_PROJECT_ID, CI_MERGE_REQUEST_IID, CI_JOB_TOKEN, etc.)GITLAB_* (GITLAB_USER_LOGIN, etc.)PROJECT_*, MR_* variables set by CIThese are required for CI automation, not security issues:
--dangerously-skip-permissions (required for non-interactive CI)--output-format text (standard CI output)--print with MCP servers--no-verify in CI pipeline contextsCI jobs run in isolated, ephemeral containers:
/tmp or CI workspace directoriesDismiss findings that match these patterns:
If you're unsure, apply this test: "Would a senior engineer reviewing this MR request this change?" If the answer is "probably not", DISMISS IT.
Also ask: "Is this finding actionable and specific?" If the finding is vague or the fix is unclear, DISMISS.