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.
npx skills add perforce/p4mcp-server --skill p4-code-reviewgit clone --depth 1 https://github.com/perforce/p4mcp-serverWrote 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.
[](https://agentmods.dev/skills/perforce/p4mcp-server/p4-code-review)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01107 |
| Opus 5.5 | $0.00000 | $0.00443 |
| Sonnet 5.5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00111 |
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 1mo 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.
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 |
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.
- 1mo ago First seen · 103 lines · 0 tokens per session scan A 0cefc2113f3f
p4-code-review is a skill published in the GitHub repository perforce/p4mcp-server (122 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,107 tokens. 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.
Other skills, from other repositories
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
zen-review
Expert code reviewer. Analyze PR changes for correctness, security, performance, and quality. Returns findings as JSON. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
reviewing-update-sets
Reviewing, analyzing, and comparing ServiceNow update sets before promotion, singly or in batches. Shows changes, risks, dependencies, and conflicts. Use when the user mentions update sets, customizations, promotion, code review, change tracking, pre-deployment review, sysupdatexml, customer updates, 'what changed in…
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
audit-architecture
Audit module coupling, cohesion, hidden dependencies, and design smells. Use when conducting architecture reviews, evaluating design decisions, or identifying structural tech debt.