rtk-skill

rtk-skill is a skill for Claude Code, Codex from sopaco/cowork-forge. It costs 53 tokens per session (1,760 once invoked), scanned A, original, MIT.

A command-line helper that shortens the output from commands such as tests, builds, Git, and package managers before it reaches the coding agent.

In plain words
What is it for?
Use it when running verbose shell commands in a Terrain project. Prefix supported commands with `rtk`; it can use an installed Terrain binary or run through Bun or Node.
Why use it?
Long command output uses the agent's context on information you may not need. It filters and compresses that output so the agent can focus on the useful parts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add skills/sopaco/cowork-forge/rtk-skill
Any agent
npx skills add sopaco/cowork-forge --skill rtk-skill
Clone the repo
git clone --depth 1 https://github.com/sopaco/cowork-forge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for rtk-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/sopaco/cowork-forge/rtk-skill.svg)](https://agentmods.dev/skills/sopaco/cowork-forge/rtk-skill)
Your own site
<a href="https://agentmods.dev/skills/sopaco/cowork-forge/rtk-skill"><img src="https://agentmods.dev/badge/skills/sopaco/cowork-forge/rtk-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01760
Opus 5 $0.00026 $0.00880
Sonnet 5 $0.00011 $0.00352
Haiku 4.5 $0.00005 $0.00176

Measured 6d ago against content hash df03475370c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rtk-skill 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 6d 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.

.agents/skills/rtk-skill/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTK Skill (Rust Token Killer)

RTK is a CLI proxy that filters and compresses command output before it reaches the LLM (typically 60–90% token savings).

Resolve the RTK command (read first)

Use conventional paths only — never machine-specific absolute paths like /Users/... or C:\Users\....

On Windows, tools deploy to %USERPROFILE%\.terrain\bin\ (also written as ~/.terrain/bin/ in Git Bash / PowerShell 7+). Binaries use .exe extensions; PATHEXT resolves rtkrtk.exe.

Priority Command prefix When
1 ~/.terrain/bin/rtk Terrain env integration or desktop app (see existence check below)
2 bunx @terrain-ai/rtk No Terrain install; needs network once
3 npx @terrain-ai/rtk Same as bunx if Bun unavailable

Optional manifest (local, gitignored): .terrain/env/agent-tools.json — same ~/.terrain/bin/… conventions.

Existence check (cross-platform):

Shell Check
bash / zsh / Git Bash [ -x ~/.terrain/bin/rtk ] || [ -x ~/.terrain/bin/rtk.exe ]
PowerShell Test-Path "$HOME\.terrain\bin\rtk.exe"
cmd if exist "%USERPROFILE%\.terrain\bin\rtk.exe"

Shell rules:

  • Invoke as ~/.terrain/bin/rtk <cmd> — tilde expands at word start in bash/zsh/Git Bash/PowerShell 7+.
  • Do not export RTK="$(jq -r .rtk …)" then "$RTK" — quoted variables do not expand ~.
  • Do not assume bare rtk is on PATH.

Example (pick one prefix per session after the existence check):

# bash / Git Bash
if [ -x ~/.terrain/bin/rtk ] || [ -x ~/.terrain/bin/rtk.exe ]; then
  PREFIX=~/.terrain/bin/rtk
else
  PREFIX="bunx @terrain-ai/rtk"
fi
$PREFIX git status
# PowerShell
$PREFIX = if (Test-Path "$HOME\.terrain\bin\rtk.exe") { "$HOME\.terrain\bin\rtk.exe" } else { "bunx @terrain-ai/rtk" }
& $PREFIX git status

Verify:

~/.terrain/bin/rtk gain || bunx @terrain-ai/rtk gain

Read the full file on GitHub · 214 lines

Changes

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.

  1. 6d ago First seen · 214 lines · 53 tokens per session scan A df03475370c1

Subscribe to this mod's changes

rtk-skill is a skill published in the GitHub repository sopaco/cowork-forge (92 stars, last pushed 11d ago), licensed MIT. It adds 53 tokens to every session and 1,760 once invoked, about $0.0003 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.