DEV Community
Your AI agent skills are an unversioned dependency
Your AI agent skills are an unversioned dependency A skill is a prompt that lands in a model's system context. Most teams install them the way we installed libraries in 2009: clone a repo, copy a folder, hope nobody touches it. Then the folder drifts and the agent quietly loads something nobody reviewed. I maintain Skillporter, a package manager for AI agent skills. This is the design problem behind it, not a feature tour. The real problem is paths, not prompts Every harness reads skills from a different directory: Claude Code .claude/skills
OpenAI Codex .agents/skills
Cursor .agents/skills
GitHub Copilot .github/skills
Windsurf .windsurf/skills
Cline .cline/skills
OpenCode .opencode/skills
Hermes Agent $HERMES_HOME/skills
Eight harnesses share .agents/skills as their primary project path, and six more read it as a documented compatibility path. That directory is the trap. Remove a skill to clean up Cursor and you have just broken Codex, Gemini CLI, Zed, OpenHands and Goose for the rest of the team. Two other approaches fail in predictable ways. Symlinks break inside Docker builds, git worktrees and Windows checkouts. Copy scripts drift, because nothing records what the copy was supposed to be. Treat the skill as a dependency The package manager model maps cleanly: a manifest you commit, listing skills and target harnesses a resolution step that fetches sources and validates structure a static scan before anything is written one install per harness path, with shared paths written once a lockfile with a content hash per skill snapshots, so rollback is possible after a bad upstream change uvx skillporter add anthropics/skills --skill pdf --harness all Real output from a clean workspace: + Installed pdf across 19 harness(es) (+12 created, ~0 updated, =7 deduplicated/unchanged)
+ Claude Code created (copy via .claude/skills)
+ GitHub Copilot created (copy via .github/skills)
+ Hermes Agent created (copy via .hermes/skills)
Twelve directories, seven shared paths deduplicated. That tally is the whole argument for a resolver: a copy script would have written nineteen copies and called it success. Drift is the thing worth detecting Once a skill is pinned, the interesting question stops being what is installed and becomes what changed. skillporter sync # reconcile workspace with manifest, write the lock
skillporter lock --check # exit 1 on drift, exit 2 if the check could not run
skillporter outdated # compare version, commit and tree hash upstream
skillporter rollback pdf # restore the last snapshot
The exit code split matters more than it looks. A pipeline needs to distinguish a failed check from a check that never ran, otherwise a broken tool reads as a pass. Skills are a supply chain input, so be honest about scanning A static scanner finds known dangerous patterns: curl piped to shell, base64 payloads, credential reads, risky permission requests. It reports finding codes and a risk score, and it never executes skill code during install. What it cannot do is catch novel prompt injection written in ordinary prose. A URL can serve harmless content when inspected and something else when the agent fetches it later. If a vendor tells you their scanner proves a skill is safe at runtime, they are selling you certainty they do not have. The docs for this one say so explicitly, which is the main reason I trust the rest of them. Read-only by default when a model is the caller The MCP mode is worth a paragraph. An MCP server is designed to be called by a model, which means its arguments may be hostile. So the server exposes detect, diagnose, scan, inspect and matrix, and denies add, install, sync and remove unless started with --allow-writes. The workspace root comes from a flag or an environment variable, not from tool arguments, and traversal, escaping symlinks and UNC paths are rejected. What this is not Not a ma...
Powered by Readybot.io
External Link
Platform
You are about to visit:
https://example.comThis will open in a new tab. Make sure you trust this link.