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 agentmods add instructions/iprabhu/mcp-perforce-server/agents-mdgit clone --depth 1 https://github.com/iPraBhu/mcp-perforce-serverWhat 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 | $0.05893 | $0.05893 |
| Opus 5 | $0.02946 | $0.02946 |
| Sonnet 5 | $0.01179 | $0.01179 |
| Haiku 4.5 | $0.00589 | $0.00589 |
Grade A, and why
mcp-perforce-server AGENTS.md 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 yesterday.
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 — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Perforce Server Agents
This document describes all available agents (tools) provided by the MCP Perforce Server. Each agent corresponds to a specific Perforce operation that can be invoked through the Model Context Protocol.
MCP clients are advertised underscore-safe tool names such as p4_changes; the dotted names below remain accepted as backward-compatible aliases.
Agent Categories
Repository Operations
p4.info
Description: Get Perforce server and client information
Parameters:
workspacePath(optional): Path to workspace directory
Returns: Server info including user, client, server version, and configuration details
p4.status
Description: Get workspace status including opened files and pending changes
Parameters:
workspacePath(optional): Path to workspace directory
Returns: Status of opened files, pending changelists, and workspace state
p4.sync
Description: Sync files from the depot to workspace
Parameters:
filespec(optional): Single filespec to syncfilespecs(optional): Multiple filespecs to sync in one commandforce(optional): Force sync even if files are openedpreview/summaryPreview(optional): Preview full sync or summary-only previewmetadataOnly/safeSync/populateOnly(optional): Native-k,-s, or-psync modesquiet,reopenMoved,useListOptimization,max,parallel(optional): Additional native sync controlsworkspacePath(optional): Path to workspace directory
Returns: Sync results with file statistics
p4.opened
Description: List all opened files in the workspace
Parameters:
changelist(optional): Filter by changelist numberfiles(optional): Limit the result to specific files/filespecsworkspacePath(optional): Path to workspace directory
Returns: List of opened files with their status and changelist information
p4.have
Description: List files that are synced to the workspace
Parameters:
filespec(optional): Single filespec to checkfilespecs(optional): Multiple filespecs to check in one commandworkspacePath(optional): Path to workspace directory
Returns: List of synced files with revision information
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.
- yesterday First seen · 572 lines · 5,893 tokens per session scan A 04b7b8541ba2
mcp-perforce-server AGENTS.md is an instructions file published in the GitHub repository iPraBhu/mcp-perforce-server (1 stars, last pushed 3mo ago), licensed MIT. It adds 5,893 tokens to every session, about $0.0295 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.