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/dais-polymtl/flock/copilot-instructionsgit clone --depth 1 https://github.com/dais-polymtl/flockWhat 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 | $0.01406 | $0.01406 |
| Opus 5 | $0.00703 | $0.00703 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
flock copilot-instructions.md 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 3d 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.
- **Key dependencies**: `nlohmann-json`, `curl`, `gtest` (see `vcpkg.json`) How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for Flock
Overview
Flock is a C++ DuckDB extension that integrates LLMs (Large Language Models) and RAG (Retrieval-Augmented Generation) into DuckDB through declarative SQL queries. It supports OpenAI, Azure, and Ollama providers and enables semantic functions such as llm_complete, llm_filter, llm_embedding, and hybrid search directly from SQL.
- Language: C++17
- Build system: CMake (3.5+) with DuckDB's extension CI tools (
extension-ci-tools/) - Dependency manager: vcpkg (managed via
vcpkg.json) - Key dependencies:
nlohmann-json,curl,gtest(seevcpkg.json) - DuckDB version targeted: v1.5.3 (see
MainDistributionPipeline.yml)
Repository Layout
.
├── CMakeLists.txt # Top-level CMake (builds static + loadable extension, unit tests)
├── extension_config.cmake # DuckDB extension load config (references this repo)
├── vcpkg.json # vcpkg dependency manifest
├── Makefile # Convenience targets (lf_setup, lf_setup_dev)
├── scripts/
│ ├── build_and_run.sh # Interactive guided build + run script
│ ├── build_project.sh # Non-interactive build script
│ └── setup_vcpkg.sh # vcpkg bootstrap
├── src/
│ ├── flock_extension.cpp # Extension entry point (LoadInternal, FlockExtension::Load)
│ ├── include/flock/ # Public headers
│ ├── core/ # Config, common utilities
│ ├── functions/ # Scalar and aggregate SQL functions
│ ├── model_manager/ # Provider integrations (OpenAI, Azure, Ollama)
│ ├── prompt_manager/ # Prompt management
│ ├── secret_manager/ # API key/secret handling
│ ├── registry/ # Model/prompt registries
│ ├── metrics/ # Metrics collection
│ └── custom_parser/ # Custom SQL parser extension
├── test/
│ ├── unit/ # C++ unit tests (GTest), built via CMake
│ └── integration/ # Python integration tests (pytest, uv)
├── duckdb/ # DuckDB source submodule
├── extension-ci-tools/ # DuckDB extension CI/build helpers submodule
├── .clang-format # clang-format config (LLVM style, IndentWidth=4, ColumnLimit=0)
├── .cmake-format # cmake-format config
└── .pre-commit-config.yaml # Pre-commit hooks: clang-format v18.1.8, cmake-format v0.6.13
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.
- 3d ago First seen · 128 lines · 1,406 tokens per session scan A c790ca19975a
flock copilot-instructions.md is an instructions file published in the GitHub repository dais-polymtl/flock (355 stars, last pushed 1mo ago), licensed MIT. It adds 1,406 tokens to every session, about $0.0070 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
GPT-RAG config-python.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
gpt-rag-mcp AGENTS.md
Instructions for Azure/gpt-rag-mcp, covering gpt-rag mcp engineering-agent contract, priority, what this repository is, repository boundaries and how to work.
gemini-cli-extension GEMINI.md
Instructions for pinecone-io/gemini-cli-extension, covering pinecone extension for gemini cli, available agent skills, key concepts & setup and available mcp tools.