codebase-review

A command for reviewing code changes through a write, review, fix, and confirmation workflow. It checks an actual Git diff rather than reviewing unchanged code.

In plain words
What is it for?
Use it to review uncommitted changes or compare a branch with a Git reference such as main, then recheck high- or critical-severity findings.
Why use it?
It prevents meaningless reviews when there are no changes and focuses fixes on confirmed serious defects.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mgd34msu/goodvibes-plugin/codebase-review
Clone the repo
git clone --depth 1 https://github.com/mgd34msu/goodvibes-plugin
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00946
Opus 5 $0.00026 $0.00473
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00005 $0.00095

Measured 2d ago against content hash b167d2025ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/goodvibes/commands/codebase-review.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase review (WRFC)

Runs the Write-Review-Fix-Confirm loop against an actual diff. Three properties define it. It is diff-triggered, so it never runs against unchanged code and never fires off an agent type. Grounded checks outrank model opinion. Findings are refutation-based rather than a single approve or reject score. See the task-orchestration skill for the WRFC pattern and the review-scoring skill for the rubric this command's reviewer step uses.

Usage

/goodvibes:codebase-review              # review uncommitted working-tree changes
/goodvibes:codebase-review main         # review the diff against `main`

Instructions

Step 1: determine the diff (diff-triggered, not always-on)

# Uncommitted changes (default):
git diff --stat && git diff

# Against a base ref, if $ARGUMENTS names one:
git diff --stat "$ARGUMENTS"... && git diff "$ARGUMENTS"...

If the diff is empty, stop here and say so plainly:

No changes to review (diff against <target> is empty).

Do not spawn a reviewer over zero changes. That produces a meaningless 10/10-by-definition "pass" and wastes a review cycle, which is exactly the failure mode this command is designed to avoid.

Step 2: grounded checks first

Before any model-opinion review, run whatever the project actually has configured. Read package.json scripts (or the equivalent for the project's language/toolchain) rather than assuming npm run typecheck exists. Typical set, run only what's present:

npm run typecheck --if-present
npm run lint --if-present
npm test --if-present -- --run

Capture the real pass/fail output. These results outrank any subjective finding in the review step below. A test failure or a type error is not a "finding to weigh," it's a fact.

Step 3: refutation review

Spawn the refutation-reviewer agent (Task tool) with:

  • The diff from Step 1 (or a summary + code_grep/code_read pointers if it's large; don't truncate silently, say what was omitted).
  • The grounded-check results from Step 2.
  • Instruction: apply the review-scoring rubric, a ranked defect list with severity and a CONFIRMED/PLAUSIBLE verdict per finding, not a scalar score.

Read the full file on GitHub · 105 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 105 lines · 53 tokens per session scan A b167d2025ef3

Subscribe to this mod's changes

codebase-review is a command published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 946 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.