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/personamanagmentlayer/pcl/copilot-instructionsgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/instructions/personamanagmentlayer/pcl/copilot-instructions)<a href="https://agentmods.dev/instructions/personamanagmentlayer/pcl/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/personamanagmentlayer/pcl/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.08233 | $0.08233 |
| Opus 5 | $0.04117 | $0.04117 |
| Sonnet 5 | $0.01647 | $0.01647 |
| Haiku 4.5 | $0.00823 | $0.00823 |
Grade A, and why
pcl copilot-instructions.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 5d 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 — 1,383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for PCL (Persona Control Language)
Project Overview
PCL (Persona Control Language) is a domain-specific programming language and compiler for AI persona management. This is a TypeScript-based compiler project that includes:
- Lexer: Tokenization and scanning
- Parser: AST generation from tokens
- Semantic Analysis: Type checking, validation, and symbol resolution
- Runtime: Execution engine for PCL programs
- Standard Library: Built-in personas, types, and utilities
- CLI: Command-line interface for PCL tools
Tech Stack: TypeScript 5.3+, Node.js, ESM modules, Vitest for testing
PCL Bootstrap System
Important: This project includes a PCL-Lite Bootstrap system that enables AI assistants to interpret /persona commands for multi-persona collaboration.
- Bootstrap File:
../.roadmap/bootstrap/BOOTSTRAP_EN.md - Purpose: Embedded runtime v1.0 for AI chat interfaces (ChatGPT, Claude, Gemini, etc.)
- Personas: 25+ built-in personas (ARCHI, SEC, DEV, DEVOPS, CRITIC, etc.) with specialized skills
- Commands: 120+
/personacommands for activation, composition, teams, workflows, and more - Domain Focus: Standardization personas (STANDARD_ARCHITECT, SPEC_EDITOR, COMPLIANCE_ENGINEER, etc.)
When working on PCL code generation, reference the bootstrap specification to understand the target runtime behavior and persona system that PCL compiles to.
Key Bootstrap Concepts:
- Persona Activation:
/persona [id]- Activate a persona with specialized capabilities - Team Composition:
/team [id]- Load pre-configured teams (e.g., security-review, dream-team, standardization) - Shared Skills: Personas inherit foundation, technical, security, architecture, standards, and tools skills
- Merge Modes:
primary,consensus,weighted,sequential,parallelfor multi-persona responses - Workflow Orchestration: Define and execute multi-step workflows with persona handoffs
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.
- 5d ago First seen · 1,383 lines · 8,233 tokens per session scan A a06d709fd1b1
pcl copilot-instructions.md is an instructions file published in the GitHub repository personamanagmentlayer/pcl (41 stars, last pushed today), licensed Apache-2.0. It adds 8,233 tokens to every session, about $0.0412 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 2026-08-30.
Other instructions, from other repositories
deepthonk AGENTS.md
AGENTS.md instructions for linxule/deepthonk: DeepThonk is a provider-neutral, OpenDeepThink-style reasoning optimizer exposed as a TypeScript CLI and MCP server.
langgraphjs CLAUDE.md
Claude Code instructions for langchain-ai/langgraphjs, covering langgraphjs development guide, corridor security analysis, build & test commands, code style guidelines and library architecture.
langgraphjs AGENTS.md
AGENTS.md instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.
parlant CLAUDE.md
Instructions for emcie-co/parlant: This is the main repo of Parlant (https://parlant.io).
blade-code AGENTS.md
AGENTS.md instructions for echoVic/blade-code, covering agents.md, project overview, quick commands, development and running.
Kokoro-Engine CLAUDE.md
Claude Code instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.