p4-plan-mentions

p4-plan-mentions is a skill for Claude Code, Codex from perforce/p4plan-mcp. It costs 67 tokens per session (1,047 once invoked), scanned A, original, MIT.

A guide to making @mentions in P4 Plan comments and multiline fields appear as links to the referenced user. It uses the user's existing account link rather than guessing one.

In plain words
What is it for?
Use it when addressing a teammate, notifying someone, or referring to a user inside a comment, description, or reproduction step.
Why use it?
It helps mentions open the correct user and render properly in both the desktop and web clients.

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/p4plan-mcp/mentions
Any agent
npx skills add perforce/p4plan-mcp --skill mentions
Clone the repo
git clone --depth 1 https://github.com/perforce/p4plan-mcp

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-plan-mentions

README.md
[![agentmods](https://agentmods.dev/badge/skills/perforce/p4plan-mcp/mentions.svg)](https://agentmods.dev/skills/perforce/p4plan-mcp/mentions)
Your own site
<a href="https://agentmods.dev/skills/perforce/p4plan-mcp/mentions"><img src="https://agentmods.dev/badge/skills/perforce/p4plan-mcp/mentions.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,047 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 $0.00067 $0.01047
Opus 5 $0.00034 $0.00524
Sonnet 5 $0.00013 $0.00209
Haiku 4.5 $0.00007 $0.00105

Measured 4d ago against content hash 26546e2b97f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

p4-plan-mentions 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/mentions/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@Mentions in P4 Plan Comments

A mention is a regular HTML anchor whose href is the user's userLink URL. Both clients render it as a styled link; clicking it opens the user.

Format

<a href="<USER_LINK>">@<DISPLAY_NAME></a>
  • <USER_LINK> — the user's userLink field. Always copy this verbatim from the GraphQL response — never construct it by hand. It looks like hansoft://<server>;<database>;<guid>/UserID/<numeric_id> but the host/database/guid prefix is connection-specific and you don't know it.
  • <DISPLAY_NAME> — the user's display name. Prepend a literal @. The clients show this verbatim — they do not auto-resolve names or auto-prepend @.
Source Tool Field
The current authenticated user get_current_user userLink
Members of a project list_project_users users[].user.userLink

Both tools now return userLink as a normal field. Copy it verbatim.

Examples

Single mention

<html><body><p>Can you take a look, <a href="hansoft://server;db;guid/UserID/42">@Alice</a>?</p></body></html>

Two mentions in a paragraph

<html><body><p>cc <a href="hansoft://server;db;guid/UserID/42">@Alice</a> and <a href="hansoft://server;db;guid/UserID/77">@Bob</a> — please review.</p></body></html>

Mention inside a list item

<html><body>
<ul style="margin-top:0px;margin-bottom:0px">
  <li>Reviewed by <a href="hansoft://server;db;guid/UserID/42">@Alice</a>.</li>
</ul>
</body></html>

Rules and gotchas

  • @ is literal. Both clients display the link text verbatim — they do not auto-prepend @ or resolve display names. Always include the @ and the name yourself.
  • Don't put a mention inside <pre> or <code>. Code blocks suppress link styling and the chip will render as plain text.
  • Percent-encode special characters in the URL. Spaces become %20, > becomes %3E. The userLink returned by the API is already correctly encoded — copy it verbatim and don't modify.
  • One <a> element per mention. Don't wrap multiple @names in a single <a>.
  • Mentions live inside the HTML body, not at the top level — wrap your comment in <html><body><p>...</p></body></html> if it contains a mention. See the comment-html-format skill for the surrounding format.

Read the full file on GitHub · 80 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 · 80 lines · 67 tokens per session scan A 26546e2b97f2

Subscribe to this mod's changes

p4-plan-mentions is a skill published in the GitHub repository perforce/p4plan-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,047 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.

Related

Other skills, from other repositories

p4-code-review

P4 code review workflows — discover, create, vote, comment, transition, and manage reviews via P4 MCP tools. Use when: creating reviews, voting, commenting, transitioning review states, managing participants, or tracking review activity in P4.

perforce/p4mcp-server · 55 tokens

p4-file-operations

P4 file operations — query content, history, annotations, diffs, and modify files (add, edit, delete, move, sync, resolve) via P4 MCP tools. Use when: reading file content, viewing history, comparing revisions, adding or editing files, syncing, resolving conflicts, or reconciling workspace changes in P4.

perforce/p4mcp-server · 76 tokens

p4-stream-workflows

P4 stream workflows — creation, branching, merging, copying, integration, switching, and spec management via P4 MCP tools. Use when: creating streams, branching, merging, copying between streams, integrating changes, switching workspaces, or managing stream specs in P4.

perforce/p4mcp-server · 61 tokens

p4-changelist-management

P4 changelist workflows — create, list, submit, shelve, unshelve, and manage changelists and shelved files via P4 MCP tools. Use when: creating changelists, editing files, shelving, unshelving, submitting, organizing changes, or managing pending work in P4.

perforce/p4mcp-server · 71 tokens

p4-workspace-setup

P4 workspace setup and management — create, configure, sync, and switch workspaces via P4 MCP tools. Use when: creating workspaces, configuring client specs, syncing files, switching workspaces, or checking workspace status in P4.

perforce/p4mcp-server · 56 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens