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/agents-mdgit 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 | $0.00653 | $0.00653 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
conch 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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - R-Shell
Project Summary
R-Shell is a Rust-native command-line SSH workspace. The app lives in cli/ and
is a single clap-based CLI binary named r-shell. There is no graphical UI.
Core features currently in scope:
- saved SSH connection management (
connectionssubcommand) - password and private-key auth
- one-shot remote command execution (
exec) - interactive PTY shell (
shell) - remote directory listing (
ls) - single-file SFTP upload/download (
upload/download) - remote system resource snapshot (
stats) - local MCP Streamable HTTP server at
http://127.0.0.1:9123/mcp(mcp), including persistent SSH sessions (ssh_session_open/ssh_exec/ssh_read_file/ssh_write_file/ssh_list_dir) that reuse one connection across calls
Key Files
| Area | File |
|---|---|
| CLI entry, arg parsing, commands | cli/src/main.rs |
| Workspace models | cli/src/model.rs |
| Local persistence | cli/src/storage.rs |
| SSH/PTY/SFTP | cli/src/ssh.rs |
| Connection manager | cli/src/native_backend.rs |
| Remote system monitor | cli/src/monitor.rs |
| MCP server | cli/src/mcp.rs |
Commands
pnpm dev # run the CLI (cargo run)
pnpm run check # cargo check
pnpm test # cargo test
pnpm run build # cargo build
pnpm run fmt # cargo fmt
Direct Cargo commands are also fine:
cargo run --manifest-path cli/Cargo.toml
cargo check --manifest-path cli/Cargo.toml
cargo test --manifest-path cli/Cargo.toml
cargo build --manifest-path cli/Cargo.toml
CLI Direction
r-shell is a focused, scriptable command-line tool. Keep it that way:
- Subcommands map to single responsibilities (
connections,exec,shell,ls,upload,download,stats,mcp). - A remote target is either a saved connection (
-c <id|name>) or ad-hoc--host/--userflags. - Prefer plain, greppable output; offer
--jsonwhere structured output helps. - Never echo secrets; prompt for missing passwords without echo.
- One-shot commands connect, do their work, and disconnect within a single
invocation.
shelluses crossterm raw mode for an interactive PTY.
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 · 73 lines · 653 tokens per session scan A 5a5efb8f0a64
conch AGENTS.md is an instructions file published in the GitHub repository MageGojo/conch (3 stars, last pushed 23d ago), licensed MIT. It adds 653 tokens to every session, about $0.0033 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
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).
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.
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.