Review code changes with an independent agent from a different model provider. After tests pass, check a fixed diff against acceptance criteria, send blocking issues back to the implementer, and repeat until review passes.
中文简介正在准备中。当前显示英语简介。
Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.
安装前可以查看交给 AI 代理的指令内容。
The implementer never signs off on its own work — a different model does, and review is a sub-agent that returns a structured report, not a transcript anyone needs to read through.
gh pr diff <pr> > <absolute shared diff path> or
git -C .worktrees/<task_id> diff <base-sha>...<head-sha> > <absolute shared diff path>).
Use a unique snapshot outside the implementer's worktree, record its base and
head commit SHAs, and leave it unchanged until review finishes. The reviewer
must be able to read that path. For a different host or sandbox, transfer the
snapshot first or arrange access to both commits so it can compute the diff;
never regenerate the diff through model output.sys_os_shell. If red, re-dispatch the implementer to drive it green first;
don't involve the reviewer yet.
If a pytest result's count must be recorded or reconciled, collect ground
truth with python -m pytest --collect-only -q <same files> against the
exact file set/command/commit the implementer reported. Never use
grep -c 'def test_' as a pytest count: it counts functions, not collected
cases, and misses parametrized case expansion.claude_code, codex,
opencode, cursor, hermes, agy, or pi (e.g. Claude built it → any of
codex / opencode / cursor / hermes / agy / pi, and so on). Use a
task-based title such as review-auth-refactor, never the raw vendor name:
sys_session_send(agent="claude_code"|"codex"|"opencode"|"cursor"|"hermes"|"agy"|"pi", title="review-<task_slug>", args={purpose: "review", input: "Read the diff at <absolute shared diff path> (base <base-sha>, head <head-sha>). <The acceptance contract>. Review ONLY against the contract. Report blocking / non-blocking / suggestions. Do not edit code. If the snapshot is inaccessible, report that failure rather than reviewing from a summary."}). Pass the snapshot path,
not its contents; do NOT point the reviewer at the implementer's worktree.
Prepare the snapshot and emit the
sys_session_send call in the SAME turn you decide to review — never end a
turn having only announced "I'll load cross-review and fetch the diff" with
no tool call (that dropped turn stalls the run; nothing dispatches and no
inbox wake arrives). Once the reviewer dispatch is in flight, end your turn;
collect the inbox-delivered structured report with sys_read_inbox when it
returns. Use sys_session_get_history only to debug an empty or unclear
review result.sys_session_send — reuse the original implementer's
agent + title (or address it by session_id) with
purpose: "implement", so the worker keeps its worktree/branch context and
updates its existing PR. A new title would spawn a fresh worker with no
memory of the task. Then loop to step 1.claude_code/codex/opencode/cursor/hermes/agy/pi) dispatched with
purpose: "review" — a DIFFERENT vendor from the one that built the diff. It
reports issues and never edits; only the implementer opens a PR, so a stray
reviewer edit never reaches the deliverable.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Test Omnigent’s native Antigravity integration with a live local server and the real agy CLI. Verify messages traveling between the web interface and terminal, mirrored replies, permission requests, interruption, session resumption, and process cleanup.
中文简介正在准备中。当前显示英语简介。
Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.
中文简介正在准备中。当前显示英语简介。
Create reference documentation directly from source code for public functions, classes, command-line commands, and endpoints. Organize parameters, defaults, return values, errors, and runnable examples, then check that the documentation matches the implementation.
中文简介正在准备中。当前显示英语简介。
Create an Omnigent agent directory using validated templates for configuration and instructions. Choose how the agent runs, then add web search, shell access, external tool connections, or subagents only when the task requires them.
中文简介正在准备中。当前显示英语简介。
Turn a selected range of commits or merged pull requests into release notes grouped by change type. Describe user-visible effects, link to supporting changes, and highlight breaking changes so readers can assess an upgrade.
中文简介正在准备中。当前显示英语简介。
Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.
中文简介正在准备中。当前显示英语简介。