Skip to main content
Glama
KentQi

cc-code-review

by KentQi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

claude_code_review

Run a confidence-scored code review on a repo, PR, branch, or commit using parallel reviewer agents, then get a markdown report.

Instructions

Run Claude Code's code-review skill (5 parallel reviewer subagents, 0-100 confidence scoring, keeps findings >=80) on a repository and return the markdown report. Costs Claude API credits; a run typically takes 2-15 minutes. Afterwards, fix the code and re-run to verify, or use claude_review_followup with the returned session_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
prNoGitHub PR number or URL, e.g. "123" or "owner/repo#123" (for scope=pr, or as first choice in auto)
fixNoFix mode: after the report, Claude Code edits the repo files to fix the confirmed findings (Edit only, no git commands, no commit; .git and secret paths are deny-listed). Adds a '## Fixes Applied' section.
focusNoExtra review focus or instructions, e.g. '重点看并发安全'
modelNoClaude model override (passed as --model)
scopeNoauto: PR if pr given / branch ahead of default / working-dir changes / last commitauto
effortNoReview effort / reasoning level, same scale as Claude Code (--effort): low..max. max/xhigh = exhaustive deep review, slower and pricier.high
baseRefNoBase branch/tag for scope=branch (default: auto-detect the default branch)
maxTurnsNoAgentic turn cap for the review session
postToPRNoAlso post the summary comment to the GitHub PR via gh (default false — report only)
repoPathYesAbsolute path to the git repository to review (the review runs with cwd=repoPath; ~/ prefix allowed)
maxBudgetUsdNoAPI spend cap for this run via --max-budget-usd (default 5); 0 disables. On third-party gateways this depends on usage data the gateway returns.
outputLanguageNoLanguage for the report, e.g. "中文" or "English"中文
timeoutMinutesNoHard wall-clock timeout for the run
installSkillIfMissingNoAuto-install the bundled code-review skill into ~/.claude/skills when missing (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.6.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so the description carries the load, and it does disclose the costly, long-running nature (Claude API credits, 2-15 min) and the scoring threshold. It does not address permissions or whether the fix mode alters repo state beyond what the schema's 'fix' description states. The cost/latency disclosure is the key value-add here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action and mechanism, then cost/time reality, then the routing alternatives. Nothing is wasted and the critical constraints appear first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter, mutation-capable, paid, long-running tool with no output schema, the description gives an agent the essentials: cost, duration, scoring behavior, and a follow-up path. It could be slightly stronger on what happens to the repo in fix mode, but the schema's fix description covers that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with detailed per-parameter descriptions (e.g. fix mode edits, scope auto logic, budget cap caveats). The description adds no parameter-level detail, so baseline 3 is correct — the schema already does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (run code-review skill on a repository) and details the mechanism (5 parallel reviewer subagents, 0-100 scoring, keeps >=80) and the return (markdown report). No sibling does this — claude_review_env and claude_review_followup are clearly different, and the description even names claude_review_followup as the follow-up path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: use it to review a repo, then fix and re-run to verify, or use claude_review_followup with the returned session_id. Names an alternative and the condition selecting it. Missing explicit 'when not to use' (e.g. vs env/precheck), but the routing is largely unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools