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-dam-workflowsgit 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-dam-workflows)<a href="https://agentmods.dev/skills/perforce/p4mcp-server/p4-dam-workflows"><img src="https://agentmods.dev/badge/skills/perforce/p4mcp-server/p4-dam-workflows/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-dam-workflows"><img src="https://agentmods.dev/badge/skills/perforce/p4mcp-server/p4-dam-workflows.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 | $0.00054 | $0.04284 |
| Opus 5.5 | $0.00022 | $0.01714 |
| Sonnet 5.5 | $0.00011 | $0.00857 |
| Haiku 4.5 | $0.00005 | $0.00428 |
Grade A, and why
p4-dam-workflows 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 23d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
P4 DAM Workflows
Prerequisites
- The P4 server must have the
P4.HTH.URLproperty set (points at the P4 DAM instance). - The server must be started with a P4 DAM API key via the
P4DAM_API_KEYenvironment variable. Without a key, P4 DAM tools are not registered at all — a warning is logged at startup. - Write tools (create, update, delete, sync) require the server to be started without
--readonly.
Tool Reference
Discovery & Navigation
| Tool | Purpose |
|---|---|
query_p4dam_projects |
List projects. Accepts search_term (matches name, short name, or description). |
query_p4dam_repositories |
List repositories in a project. Accepts search_term (matches short name). |
query_p4dam_helix_classic_branches |
List Helix Classic branches in a helix_classic repository. |
Asset Search
| Tool | Purpose |
|---|---|
query_p4dam_assets |
Search assets by keyword/filters — use when you don't have a depot path yet. |
query_p4dam_asset |
Fetch full metadata for a single known asset by depot path. |
fetch_p4dam_media |
Fetch and render a thumbnail, preview, or file image. |
regenerate_p4dam_preview |
Trigger async regeneration of thumbnail and preview for an asset revision. |
query_p4dam_assets filters: search_term, project_ids (UUIDs), repository_ids (UUIDs), path (wildcard depot path patterns, e.g. //depot/art/*.png), name (filename wildcard), tag, file_extension, exclude_file_extension, user, from_size / to_size (bytes), from_date / to_date (ISO 8601), all_revisions, max_results, offset.
query_p4dam_asset params: depot_path (required), identifier (changeset), project_id (short name or UUID), repository_id (UUID, or short name if project_id is also provided), include.
query_p4dam_asset include values:
- Default set:
commit,latest_commit,custom_attributes,weblinks,asset_bundle,asset_bundle_origin,parent_asset_bundles,helix_classic_branch_matches,stream_view_matches,sprite - Require project/repository/stream or branch context:
file_review,comments,all_comments - Extras:
file_count,scene_refs
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.
- 23d ago First seen · 323 lines · 54 tokens per session scan A 3a44f6bea199
p4-dam-workflows is a skill published in the GitHub repository perforce/p4mcp-server (122 stars, last pushed 24d ago), licensed MIT. It adds 54 tokens to every session and 4,284 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-26.
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.
p4-plan-pipeline
Guide working with P4 Plan pipelines and pipeline tasks — reading a pipeline's stages, breaking a backlog item down into pipeline sub-tasks, logging defects into a pipeline stage, and moving pipeline work forward. Use when the user mentions pipeline, pipeline task, pipeline stage, breakdown, auto-spawned tasks, or…
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.
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.
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.
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.