Dgk-gpt rrr
GLM-5 코드 리뷰. /rr의 상위 버전으로 더 강한 모델로 변경사항을 검토하고, Codex가 결과를 다시 검증해 유효한 이슈만 정리한다.
install
source · Clone the upstream repo
git clone https://github.com/dgk-dev/dgk-gpt
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/dgk-dev/dgk-gpt "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/rrr" ~/.claude/skills/dgk-dev-dgk-gpt-rrr && rm -rf "$T"
manifest:
skills/rrr/SKILL.mdsource content
/rrr
Use
glm-review --model glm-5 as the deeper paid review pass, then validate the results against the code before you trust them.
Default Flow
- Determine the exact review scope first.
- commit hash known -> commit mode
-> staged modestaged
-> PR modepr- mixed unrelated local changes -> focused diff file
- Run a health check only when auth or connectivity looks questionable:
glm-review --model glm-5 --health
- Run the review with the smallest correct input:
glm-review --model glm-5 glm-review --model glm-5 --mode staged glm-review --model glm-5 --mode pr glm-review --model glm-5 --mode commit --ref <COMMIT_HASH> glm-review --model glm-5 --diff-file /tmp/glm-review-diff.patch
- Verify every reported issue in the actual code and diff.
- Keep only confirmed issues.
- If fixes are requested or clearly in scope, apply them and rerun the closest verification.
Choosing Review Input
- committed single change:
glm-review --model glm-5 --mode commit --ref <COMMIT_HASH>
- committed subset of files:
glm-review --model glm-5 --mode commit --ref <COMMIT_HASH> --files src/a.ts src/b.ts
- custom focused diff:
GIT_ROOT=$(git rev-parse --show-toplevel) cd "$GIT_ROOT" && git diff HEAD -- <file1> <file2> ... > /tmp/glm-review-diff.patch glm-review --model glm-5 --diff-file /tmp/glm-review-diff.patch
If the diff is empty, stop and say there is nothing to review.
Validation Rules
is a reviewer, not an oracle.glm-review- Re-check referenced code paths before reporting a bug.
- Separate confirmed defects from debatable style feedback.
- If a finding depends on broader context, inspect the relevant surrounding code before accepting it.
Error Handling
Install it withcommand not found: glm-reviewnpm install -g glm-review
ExportZAI_API_KEY not set
in the shell or your normal secret-loading pathZAI_API_KEY- auth or API failure
Re-run
after refreshing credentialsglm-review --model glm-5 --health
Finish
Return:
- review scope used
- confirmed findings only
- notable false positives filtered out
- what verification ran after fixes, if any