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/alexastrum/skl/agents-mdgit clone --depth 1 https://github.com/alexastrum/sklWrote 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.
[](https://agentmods.dev/instructions/alexastrum/skl/agents-md)<a href="https://agentmods.dev/instructions/alexastrum/skl/agents-md"><img src="https://agentmods.dev/badge/instructions/alexastrum/skl/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01052 | $0.01052 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade B, and why
skl AGENTS.md scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
We enforce strict feature parity (commands, flags, platforms) with the original TypeScript `skills` npm package. Antigravity maps to `~/.gemini/config` (original IDE) and `~/.gemini/antigravity` (2.0). How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 Agent Configurations & Discovery
skl supports 40+ agent environments. It evaluates the local filesystem and environment variables to detect installed agents, routing and linking skills dynamically.
We enforce strict feature parity (commands, flags, platforms) with the original TypeScript skills npm package. Antigravity maps to ~/.gemini/config (original IDE) and ~/.gemini/antigravity (2.0).
IMPORTANT: ONLY WHEN EDITING README.md or human docs (eg --help) run /humanizer skill.
⚡ Discovery Mechanics
skl detects agents via project folders (e.g., .cursor, .cline, .zed) or environment variables (XDG_CONFIG_HOME, APPDATA, etc.):
func detectInstalledAgents(home, configHome, cwd string) []AgentType {
var installed []AgentType
for agentType, config := range Agents {
if config.DetectInstalled != nil && config.DetectInstalled(home, configHome, cwd) {
installed = append(installed, agentType)
}
}
return installed
}
🔗 Symlink Routing
Skills are mapped using relative symlinks to prevent duplication:
graph TD
A[Add Skill command] --> B{Installation Scope?}
B -->|Global: -g / --global| C1[Canonical Base: ~/.gemini/antigravity/skills]
B -->|Local: Project Default| C2[Canonical Base: .agents/skills]
C1 --> D1[Copy files to Canonical Global Dir]
C2 --> D2[Copy files to Canonical Project Dir]
D1 --> E1{Universal Agent?}
D2 --> E2{Universal Agent?}
E1 -->|Yes: antigravity| F1[No symlink needed]
E1 -->|No: claude-code| F2[Create relative symlink in home dir]
F2 --> G1[~/.claude/skills/my-skill -> ../.gemini/antigravity/skills/my-skill]
E2 -->|Yes: antigravity| H1[No symlink needed]
E2 -->|No: claude-code| H2[Create relative symlink in project dir]
H2 --> I1[.claude/skills/my-skill -> ../../.agents/skills/my-skill]
🛠️ Multi-Platform Compilation & Path Mappings
To ensure that skl can be deployed across Linux, Windows, and macOS architectures, the CLI tool resolves home directories and environments dynamically at runtime:
- Linux: Crawls
$XDG_CONFIG_HOMEor falls back to standard UNIX directories (e.g.,~/.config/). - Windows: Dynamic resolution maps to
%APPDATA%or%USERPROFILE%targets depending on user credentials. - macOS: Resolves configuration folders directly using standard
~/.gemini/configand~/.gemini/antigravitystructures.
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.
- 4d ago First seen · 79 lines · 1,052 tokens per session scan B d5ab0720807c
skl AGENTS.md is an instructions file published in the GitHub repository alexastrum/skl (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,052 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
cli AGENTS.md
AGENTS.md instructions for planetscale/cli, covering planetscale cli — agent guide, public repository safety, concepts, flag placement and correct.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
pvetui AGENTS.md
AGENTS.md instructions for devnullvoid/pvetui, covering agent instructions, initial setup, development workflow, quick reference and code quality standards.