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/p4plan-mcp --skill comment-html-formatgit clone --depth 1 https://github.com/perforce/p4plan-mcpWrote 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/p4plan-mcp/comment-html-format)<a href="https://agentmods.dev/skills/perforce/p4plan-mcp/comment-html-format"><img src="https://agentmods.dev/badge/skills/perforce/p4plan-mcp/comment-html-format/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/p4plan-mcp/comment-html-format"><img src="https://agentmods.dev/badge/skills/perforce/p4plan-mcp/comment-html-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00058 | $0.02032 |
| Opus 5.5 | $0.00023 | $0.00813 |
| Sonnet 5.5 | $0.00012 | $0.00406 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
p4-plan-comment-html-format scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
<pre><code>curl -X POST /api/login \ How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment & Multiline HTML Format
P4 Plan treats comment text and multiline field values as sanitized HTML. The server runs every payload through a whitelist sanitizer — anything outside the allow-list below is silently stripped. Both the Qt desktop client and the React web client render the stored result.
Plain text without any tags is a legal special case: it is valid HTML, so the sanitizer accepts it and the server stores it as-is. Anything with formatting, lists, links, code blocks, or @mentions must use the documented HTML subset below.
This skill covers the format. For @user references inside this HTML, see the mentions skill.
When to use
Read this skill before calling any of:
post_comment—textis sanitized HTMLupdate_comment—textis sanitized HTMLset_custom_field—valueis sanitized HTML when the column type is Multiline Textcreate_item/update_item—detailedDescriptionandstepsToReproduceare sanitized HTML (Bug only)
Wire format
The wire format is always sanitized HTML. Two practical shapes:
- Plain prose with line breaks (no tags needed): send raw text such as
Hello\nworld. Plain text is valid HTML; the sanitizer accepts it unchanged, and the server stores it as-is. - Anything formatted (bold, lists, links, mentions, code blocks, tables): wrap in
<html><body>...</body></html>and use the allowed tags below. The server sanitizes and minimizes — if the wrapped content reduces to plain text after sanitization (for example only<p>and<br>with no formatting), the envelope is stripped on storage.
Allowed tags
| Tag | Use for | Notes |
|---|---|---|
<p> |
Paragraph | Default block. Don't put CSS on it (margin/color all stripped). |
<br> |
Line break inside a paragraph | |
<strong>, <b> |
Bold | Use semantic <strong>. |
<em>, <i> |
Italic | Use semantic <em>. |
<u> |
Underline | |
<s>, <del> |
Strikethrough | |
<span> |
Inline color/highlight only | Only place where inline color / background-color survive. |
<a href="..."> |
Hyperlink | Use for @mentions (see mentions skill). External links allowed. |
<blockquote> |
Quoted text | Browser-default styling on web; indented in Qt. |
<pre>, <code> |
Code block / inline code | <pre><code>...</code></pre> for multi-line. Qt converts to its configured code font. |
<ul>, <ol>, <li> |
Lists | Add inline style="margin-top:0px;margin-bottom:0px" on <ul>/<ol> for clean Qt rendering. <ol type="...">/start honored. |
<table>, <thead>, <tbody>, <tfoot>, <tr>, <td>, <th>, <caption>, <colgroup>, <col> |
Tables | Use border attribute on <table> and style="border-collapse:collapse" for cross-client borders. |
<img src="hansoft://..."> |
Embedded image | Only hansoft:// URLs render in Qt. External URLs render in the web client only. Avoid for cross-client comments. |
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 · 140 lines · 58 tokens per session scan A b488bb2d72be
p4-plan-comment-html-format is a skill published in the GitHub repository perforce/p4plan-mcp (4 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 2,032 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
p4-dam-workflows
P4 DAM (Digital Asset Management) workflows — search, browse, tag, review, and manage digital assets via P4 MCP tools. Use when discovering, searching, filtering, reviewing, or managing assets stored in P4 DAM.
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.
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.
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.
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.
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.