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 skills/magegojo/conch/r-shell-sshnpx skills add MageGojo/conch --skill r-shell-sshgit 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 | $0.00115 | $0.02582 |
| Opus 5 | $0.00057 | $0.01291 |
| Sonnet 5 | $0.00023 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade D, and why
r-shell-ssh scanned grade D with 3 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
no-echo prompt; `connections list` only exposes `has_password` booleans. Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
--auth publickey --key-path ~/.ssh/id_ed25519 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
if curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:9123/mcp | grep -qE '^[0-9]'; then How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
R-Shell SSH Workflow
Use the local r-shell CLI for every remote-server task in this project. Save
each server once as a named connection, then always reference it by
-c <id|name>. This reuses one clean connect-do-disconnect path with stored
credentials, instead of spawning many raw ssh user@ip processes that look like
a brute-force/attack to the remote host.
Core Rule
- DO NOT run raw
ssh,scp, orsftpto reach a server in this project. - DO use
r-shellsubcommands with a saved connection (-c <id|name>). - On every use of this skill, first run Step 0 (ensure installed) and Step 1 (ensure MCP running), then do the task.
Step 0 — Ensure r-shell is installed (auto-install if missing)
Detect the binary; if absent, build/install it from this repo automatically. Do NOT ask the user — just install it.
# 1. Already installed and on PATH?
if command -v r-shell >/dev/null 2>&1; then
echo "r-shell: $(command -v r-shell)"
else
echo "r-shell not found — installing from source"
fi
If missing, install (prefer cargo install, which puts it on PATH via
~/.cargo/bin). Run from the repo root:
# Preferred: installs `r-shell` to ~/.cargo/bin (make sure that's on PATH)
cargo install --path cli
# Fallback if `cargo install` is unavailable/undesired: build in-tree.
# The binary lands at cli/target/release/r-shell
cargo build --release --manifest-path cli/Cargo.toml
- If
cargoitself is missing, stop and tell the user to install Rust from https://rustup.rs (do not attempt a silent toolchain install). - After a fallback build, invoke the binary by its full path
cli/target/release/r-shell(or viacargo run --manifest-path cli/Cargo.toml --).
For brevity the rest of this skill writes r-shell <command>; substitute the
built path or the Cargo form when r-shell is not yet on PATH.
Step 1 — Ensure the MCP server is running (auto-start)
The skill should make the local MCP server available without manual steps. It
binds to http://127.0.0.1:9123/mcp (localhost only).
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 · 231 lines · 115 tokens per session scan D 0ca87b4230b9
r-shell-ssh is a skill published in the GitHub repository MageGojo/conch (3 stars, last pushed 22d ago), licensed MIT. It adds 115 tokens to every session and 2,582 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 3 findings (asks the agent to reveal its instructions, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.