skill-compass

A natural-language dispatcher for SkillCompass, a system that routes requests to installed skills and related commands. It first checks known skill names and whether the system has been initialized.

In plain words
What is it for?
Use it to describe what you want to do in ordinary language, route the request to a matching skill, or receive setup guidance when SkillCompass is not initialized.
Why use it?
It helps users reach the relevant skill without memorizing command names. It can also explain when initial setup is required before routing a request.

Command

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 commands/evol-ai/skillcompass/skill-compass
Clone the repo
git clone --depth 1 https://github.com/Evol-ai/SkillCompass
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,441 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 $0.00000 $0.01441
Opus 5 $0.00000 $0.00720
Sonnet 5 $0.00000 $0.00288
Haiku 4.5 $0.00000 $0.00144

Measured 3d ago against content hash e6913cbe3e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-compass 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 3d 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.

commands/skill-compass.md · 100 lines

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.

/skillcompass — Natural Language Dispatcher

This command accepts free-form natural language and routes to the appropriate SkillCompass command. Also accessible as /skill-compass.

Locale: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.

Arguments

  • <message> (required): Natural language description of what the user wants to do.

Step 0: Setup-State Check

Before dispatching, check whether .skill-compass/setup-state.json exists.

  • If NOT exist: inform the user and guide to /inbox (which auto-initializes):
    • "SkillCompass is not set up yet. Type /inbox to get started."
  • If exists: proceed to Step 1.

Step 1: Skill Name Detection

Before keyword matching, check if the user's message contains a known skill name.

Read .skill-compass/setup-state.jsoninventory array. Build a list of all skill names (including collection children's qualified names like superpowers:writing-plans).

Scan the user's message for any exact match against this list. If a known skill name is found, extract it as target_skill and proceed to intent inference.

Semantic intents — accept equivalent natural-language input in any language (match by meaning, not literal keyword):

Intent Inferred route Notes
evaluate, check quality, assess, score eval-skill target_skill Evaluate the skill
improve, optimize, fix, upgrade eval-improve target_skill Improve the skill
remove, delete, drop, discard skill-inbox (locate target_skill) Guide to deletion
mute, stop tracking, ignore skill-inbox (mute target_skill) Mark as muted
rollback, revert, restore eval-rollback target_skill Roll back version
security, vulnerability scan eval-security target_skill Security scan
compare, diff versions eval-compare target_skill Version comparison
update, check for new version skill-update target_skill Check skill for updates
(no action verb, name only) skill-inbox (show target_skill details) Show details + action options

Read the full file on GitHub · 100 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. 3d ago First seen · 100 lines · 0 tokens per session scan A e6913cbe3e6b

Subscribe to this mod's changes

skill-compass is a command published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,441 tokens. 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.