skill_directory

A reference file listing the default folders where SkillFlow looks for or places agent skills. Skills are reusable instructions that coding agents can load.

In plain words
What is it for?
Checking skill directories for Claude Code, OpenCode, Codex, Gemini CLI, OpenClaw, and Copilot.
Why use it?
It helps developers know where each supported agent expects shared skills to be installed or scanned.

Agent

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 agents/shinerio/skillflow/skill_directory
Clone the repo
git clone --depth 1 https://github.com/shinerio/SkillFlow
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 380 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 $0.00380
Opus 5 $0.00000 $0.00190
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured yesterday against content hash 102921a5f71b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill_directory 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 yesterday.

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.

docs/agents/skill_directory.md · 13 lines

What it actually says

Built-in Agent Skill Directories

This file records the built-in agent directory defaults used by SkillFlow. These paths match core/agentintegration/domain/defaults.go.

Agent Reference Default push directory Default scan directories
Claude Code docs ~/.claude/skills/ ~/.claude/skills/, ~/.claude/plugins/marketplaces/
OpenCode docs ~/.config/opencode/skills/ ~/.config/opencode/skills/, ~/.agents/skills/
Codex docs ~/.agents/skills/ ~/.agents/skills/
Gemini CLI docs ~/.gemini/skills/ ~/.gemini/skills/, ~/.agents/skills/
OpenClaw docs ~/.openclaw/skills/ ~/.openclaw/skills/, ~/.openclaw/workspace/skills/
Copilot docs ~/.copilot/skills/ ~/.claude/skills/, ~/.agents/skills/, runtime-detected ~/.copilot/pkg/universal/<version>/builtin-skills/ when present
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. yesterday First seen · 13 lines · 0 tokens per session scan A 102921a5f71b

Subscribe to this mod's changes

skill_directory is an agent published in the GitHub repository shinerio/SkillFlow (24 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 380 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.