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/magegojo/conch/copilot-instructionsgit clone --depth 1 https://github.com/MageGojo/conchWhat 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 | $0.01001 | $0.01001 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
conch 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
R-Shell Copilot Instructions
Project Overview
R-Shell is a Rust-native command-line SSH workspace. The entire application lives in cli/ — there is no graphical UI, web frontend, or Tauri backend. SSH transport, persistence, and the MCP server all run inside a single clap-based CLI binary named r-shell.
Architecture
The app is a clap CLI (entry point cli/src/main.rs). Subcommands map to single responsibilities and reuse a set of UI-free core modules. A Tokio runtime is built per command invocation to drive async SSH/SFTP and the MCP HTTP server.
Subcommands
| Command | Responsibility |
|---|---|
connections list/add/update/remove |
Manage saved connections in workspace.json |
exec |
Run one remote command and print output |
shell |
Interactive PTY shell (crossterm raw mode) |
ls |
List a remote directory |
upload / download |
Single-file SFTP transfer |
stats |
One-shot remote system resource snapshot |
mcp |
Run the local MCP server |
Module Map (cli/src/)
| Module | Responsibility |
|---|---|
main.rs |
CLI entry, clap arg parsing, command handlers, output formatting |
model.rs |
Persisted workspace + connection data models (SavedConnection, TerminalTab, ConnectionStatus, PersistedWorkspace) |
storage.rs |
Local workspace persistence (load/save JSON on disk) |
ssh.rs (+ ssh/tests.rs) |
SSH, PTY, and SFTP implementation on russh / russh-sftp |
native_backend.rs |
Connection manager (NativeConnectionManager, SshConfig, AuthMethod, remote file types) |
monitor.rs |
Remote system monitoring/stats parsing and formatting |
mcp.rs |
Local MCP Streamable HTTP server |
MCP Server
A local MCP Streamable HTTP server is exposed while the app runs, bound to localhost only:
http://127.0.0.1:9123/mcp
Tools cover SSH connection management and listing open tabs. MCP responses must never include passwords, private keys, or passphrases.
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.
- 2d ago First seen · 100 lines · 1,001 tokens per session scan A 9a875371dbf9
conch copilot-instructions.md is an instructions file published in the GitHub repository MageGojo/conch (3 stars, last pushed 22d ago), licensed MIT. It adds 1,001 tokens to every session, about $0.0050 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.
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.
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).
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.