nano-step/rtk
skills/rtk/SKILL.md
Token optimizer for AI coding agents. Wraps common CLI commands with rtk to reduce LLM token consumption by 60-90%.
$ install --global
skillsauthnpx skillsauth add nano-step/skill-manager rtkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 3:46 AM157.9s2 files scanned
SKILL.md
- name:
- rtk
- description:
- Token optimizer for AI coding agents. Wraps common CLI commands with rtk to reduce LLM token consumption by 60-90%.
- compatibility:
- OpenCode with RTK binary installed
- author:
- Sisyphus
- version:
- 1.0.0
RTK — Rust Token Killer
Purpose: Reduce token consumption by 60-90% on shell commands. RTK filters and compresses command output before it reaches your context.
When This Skill Activates
This skill is loaded automatically. Once active, always prefix supported commands with rtk.
Command Mappings (MANDATORY)
When running shell commands via Bash tool, use rtk prefix for these commands:
| Instead of | Use | Savings |
|-----------|-----|---------|
| git status | rtk git status | ~80% |
| git diff | rtk git diff | ~75% |
| git log | rtk git log | ~80% |
| git add/commit/push/pull | rtk git add/commit/push/pull | ~90% |
| ls / ls -la | rtk ls | ~80% |
| cat file | rtk read file | ~70% |
| grep pattern . | rtk grep pattern . | ~80% |
| rg pattern | rtk grep pattern . | ~80% |
| npm test / cargo test / pytest | rtk test <cmd> | ~90% |
| npm run build / cargo build | rtk err <cmd> | ~80% |
| gh pr list/view | rtk gh pr list/view | ~70% |
| docker ps | rtk docker ps | ~80% |
| eslint / tsc | rtk lint / rtk tsc | ~80% |
Searching Inside node_modules / Ignored Directories
By default, rtk grep respects .gitignore rules — meaning node_modules, .nuxt, dist, etc. are excluded. This is the right behavior 99% of the time.
When you need to search inside ignored directories (debugging a library, checking an API signature, tracing a dependency bug):
# Search all files including node_modules (--no-ignore bypasses .gitignore)
rtk grep "defineStore" . --no-ignore
# Search a specific package only (combine --no-ignore with --glob)
rtk grep "defineStore" . --no-ignore --glob 'node_modules/pinia/**'
What does NOT work:
rtk grep "pattern" node_modules/pinia/— still excluded even with direct pathrtk grep "pattern" . --glob 'node_modules/**'— glob alone doesn't override .gitignore
Key flag: --no-ignore — this is the ONLY way to search ignored directories with rtk grep.
Other useful rtk grep flags
rtk grep "pattern" . -t ts # Filter by file type (ts, py, rust, etc.)
rtk grep "pattern" . -m 100 # Increase max results (default: 50)
rtk grep "pattern" . -u # Ultra-compact mode (even fewer tokens)
rtk grep "pattern" . -l 120 # Max line length before truncation (default: 80)
Commands to NOT Wrap
Do NOT prefix these with rtk (unsupported or counterproductive):
npx,npm install,pip install(package managers)node,python3,ruby(interpreters)nano-brain,openspec,opencode(custom tools)- Heredocs (
<<EOF) - Piped commands (
cmd1 | cmd2) — wrap only the first command if applicable - Commands already prefixed with
rtk
How RTK Works
Without RTK: git status → 50 lines raw output → 2,000 tokens
With RTK: rtk git status → "3 modified, 1 untracked ✓" → 200 tokens
RTK runs the real command, then filters/compresses the output. The agent sees a compact summary instead of verbose raw output.
Detection
Before using RTK commands, verify it's installed:
rtk --version
If rtk is not found, skip this skill — run commands normally without the rtk prefix.
Token Savings Reference
Typical 30-min coding session:
- Without RTK: ~150,000 tokens
- With RTK: ~45,000 tokens
- Savings: ~70%
Biggest wins: test output (rtk test — 90%), git operations (rtk git — 80%), file reading (rtk read — 70%).
Related Skills
nano-step/iamhumans
tools
VerifiedTrustedCommunity
Humanization layer for LLM conversation — makes the model sound and respond like a real, thoughtful, embodied human rather than an assistant or chatbot. Use whenever the reply will be read by a human and warmth, presence, or texture matter more than machine-readability. Triggers on any of: "human", "humans", "humanize", "humanization", "be human", "more human", "feel human", "people", "person", "real person", "real human", "friend", "friendly", "like a friend", "respond like a friend", "buddy", "talk", "talking", "talk to me", "talk like a person", "chat", "chatting", "conversation", "converse", "discuss", "discussion", "communication", "communicate", "listen", "just listen", "sit with me", "vent", "venting", "I just want to vent", "company", "presence", "stop being an AI", "stop sounding like a bot", "less corporate", "less robotic", "less formal", "warmer", "warm tone", "empathy", "empathetic", "comfort", "support me", "emotional support", "be honest with me", "be real with me", "real talk", "heart-to-heart", "deep conversation", "casual", "casual chat", "small talk", "chitchat", "say something", "tell me something", and on any emotional / relational / personal-decision / interpersonal context — grief, joy, anger, fear, shame, doubt, loneliness, dating, breakup, conflict, family, parents, sibling, friendship, marriage, divorce, in-laws, kids, parenting, work stress, burnout, career decision, quitting, firing, layoff, anxiety, depression, panic, sleep, dreams, identity, faith, doubt, meaning, mortality, celebration, milestone, achievement, gratitude, apology, forgiveness. Also loads when the user writes in non-English (any language) with emotional weight, when the user's message is shorter than 8 words and affect-laden, when the user types in lowercase fragments, when the user types in ALL CAPS with excitement, or when the user explicitly asks for a friend / mentor / older-sibling / wise-listener voice. Do NOT use for code generation, tool calls, structured data output, SQL, API contracts, or any task where machine-readability matters more than human warmth.
3SKILL.mdUpdated Jun 1, 2026
nano-step/open-design-mcp
tools
VerifiedTrustedCommunity
Use this skill whenever the user mentions open-design, od_generate_design, OD daemon, BYOK design generation, generating HTML mockups from a PRD, creating or managing Open Design projects, saving design artifacts, linting generated HTML, or any of the 10 `od_*` MCP tools (od_list_projects, od_get_project, od_create_project, od_update_project, od_delete_project, od_save_artifact, od_save_project_file, od_lint_artifact, od_compose_brief, od_generate_design). Also trigger on phrases like "generate a design", "create a mockup", "make a landing page", "list my OD projects", "the design daemon", "the streaming design tool", and on any 401/404/422 error coming from an `od_*` tool call. Covers env-var setup (`OD_DAEMON_URL`, auth modes, BYOK), the full PRD → generate → save → lint workflow, error diagnosis, and the safety rails (lint before save, never commit BYOK keys). Triggers even if the user doesn't explicitly say "open-design-mcp" — keyword matches on `od_*` tool names or "design generation" workflows are enough.
3SKILL.mdUpdated May 19, 2026
nano-step/od-workflow
tools
VerifiedTrustedCommunity
Use this skill whenever a user wants the **full Open Design experience** — discovery questions asked first, brand-spec extraction from URLs/files, TodoWrite planning with live updates, 5-dimensional self-critique, polished artifact at the end. Trigger phrases include "design with questions first", "OD-style workflow", "full interactive design brief", "make me a complete landing page" (when the user wants quality over speed), "design my pitch deck", "brand-aware multi-page site", "follow the Open Design playbook", or any request where the user is starting a new design project rather than tweaking an existing artifact. Also trigger on any request that mentions wanting brand consistency across multiple pages or that provides a brand URL/spec. Pair with the `open-design-mcp` tool-reference skill — both loaded together give an LLM the full picture (this skill = workflow choreography; that skill = tool catalog + errors). This skill explicitly does NOT trigger for one-off tweaks ("make the nav stickier", "swap slide 3 image") — use od_generate_design directly for those.
3SKILL.mdUpdated May 19, 2026
nano-step/sync-skill-to-manager
development
VerifiedTrustedCommunity
Sync a locally-developed OpenCode skill to the skill-manager npm package and (if private) the private-skills GitHub repo. Handles per-skill version bumps, public/private classification, build verification, and conventional-commit-style git push. Auto-publish to npm is handled downstream by nano-step/shared-workflows@v1 when the push to master lands. Use this skill whenever the user says 'sync skill', 'publish skill', 'push skill to manager', '/sync-skill-to-manager <name>', or asks to release/distribute a skill they just edited.
3SKILL.mdUpdated May 7, 2026