p4-code-review

p4-code-review is a skill for Claude Code, Codex from perforce/p4mcp-server. It costs 55 tokens per session (1,107 once invoked), scanned A, original, MIT.

A workflow for managing P4 code reviews, where P4 is a version-control system with a review process. It covers finding reviews, creating them, commenting, voting, changing their state, and tracking activity.

In plain words
What is it for?
It is for creating and maintaining reviews, inspecting changed files and comments, checking reviewer activity, voting, transitioning reviews, and archiving inactive ones.
Why use it?
It keeps common review actions in one agent workflow instead of requiring separate manual steps in P4 tools.

Skill for Claude CodeCodex

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 skills/perforce/p4mcp-server/p4-code-review
Any agent
npx skills add perforce/p4mcp-server --skill p4-code-review
Clone the repo
git clone --depth 1 https://github.com/perforce/p4mcp-server

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for p4-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/perforce/p4mcp-server/p4-code-review.svg)](https://agentmods.dev/skills/perforce/p4mcp-server/p4-code-review)
Your own site
<a href="https://agentmods.dev/skills/perforce/p4mcp-server/p4-code-review"><img src="https://agentmods.dev/badge/skills/perforce/p4mcp-server/p4-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 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 $0.00055 $0.01107
Opus 5 $0.00028 $0.00553
Sonnet 5 $0.00011 $0.00221
Haiku 4.5 $0.00006 $0.00111

Measured 4d ago against content hash 0cefc2113f3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

p4-code-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 4d 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.

skills/p4-code-review/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Workflows

Use the query_reviews and modify_reviews tools to manage P4 Code Review code reviews.

Querying Reviews

Action Purpose Key Parameters
list List reviews with filters review_fields, max_results
dashboard Get review dashboard for current user
get Get full review details review_id
transitions Get available state transitions review_id
files List files in a review review_id
files_readby Check which files have been read by reviewers review_id
comments Get all comments on a review review_id
activity Get review activity log review_id

Modifying Reviews

Lifecycle

Action Purpose Key Parameters
create Create a new review from a changelist change_id, description
transition Move review to a new state review_id, transition
archive_inactive Archive stale reviews not_updated_since, max_reviews
obliterate Permanently remove a review (requires approval) review_id

Voting & Participation

Action Purpose Key Parameters
vote Vote on a review (up/down/clear) review_id, vote_value
append_participants Add reviewers review_id, users, groups
replace_participants Replace all reviewers review_id, users, groups
delete_participants Remove reviewers review_id, users, groups
join Join a review as participant review_id
leave Leave a review review_id

Comments

Action Purpose Key Parameters
add_comment Add a new comment review_id, body, context
reply_comment Reply to an existing comment review_id, comment_id, body
mark_comment_read Mark a comment as read review_id, comment_id
mark_comment_unread Mark a comment as unread review_id, comment_id
mark_all_comments_read Mark all comments as read review_id
mark_all_comments_unread Mark all comments as unread review_id

Read the full file on GitHub · 103 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. 4d ago First seen · 103 lines · 0 tokens per session scan A 0cefc2113f3f

Subscribe to this mod's changes

p4-code-review is a skill published in the GitHub repository perforce/p4mcp-server (114 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,107 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 2026-08-30.

Related

Other skills, from other repositories

p4-plan-search-queries

P4 Plan Find query syntax for advanced searching. Use when user needs to search, filter, or find items by status, assignee, priority, severity, dates, custom fields, or any combination.

perforce/p4plan-mcp · 48 tokens

p4-plan-comment-html-format

Author HTML-formatted comments and multiline field values that render correctly in both the Qt desktop client and the React web client. Use when posting/editing comments, setting Multiline Text custom fields, or writing detailedDescription/stepsToReproduce on a Bug.

perforce/p4plan-mcp · 58 tokens

p4-plan-mentions

Format @user mentions inside HTML comments and multiline fields so they render as a proper link in both the Qt desktop client and the React web client. Use when the user wants to ping someone, notify a teammate, address @-name, or reference a user inside a comment / description / steps to reproduce.

perforce/p4plan-mcp · 67 tokens

p4-plan-task-management

Manage tasks, status updates, assignments, comments, and attachments in P4 Plan. Use when user mentions tasks, status, updates, assignments, my work, todo list, assign, comments, attachments, or collaboration.

perforce/p4plan-mcp · 50 tokens

p4-plan-planning

Manage sprints, releases, and sprint commitment in P4 Plan. Use when user mentions sprints, sprint planning, capacity, velocity, committing work, iterations, burndown, releases, milestones, versions, or tagging.

perforce/p4plan-mcp · 52 tokens

p4-plan-backlog-refinement

Guide backlog refinement sessions, story refinement, estimation, and prioritization in P4 Plan. Use when user mentions backlog, refinement, estimation, story points, or prioritization.

perforce/p4plan-mcp · 43 tokens