Olshansk Agent Skills
- 8 repo stars
- Updated July 27, 2026
- Olshansk/agent-skills
olshansk-agent-skills is a Claude Code plugin that captures session learnings into AGENTS.md for cross-tool agent interoperability.
About
olshansk-agent-skills is a Claude Code plugin focused on ending sessions with durable artifacts: the habits and constraints you discovered should land in AGENTS.md, not evaporate when the chat closes. developers switching between Claude Code, Cursor, and other agents waste time re-explaining repo quirks; a single AGENTS.md fed by session commit gives every tool the same playbook. The repository positions itself around installable skills, catalog updates, and workflow category fit—think of it as governance for how your agent remembers conventions, test commands, and skill invocations. Use it after meaningful implementation or debugging blocks, not for throwaway experiments. It complements hand-authored AGENTS.md sections rather than replacing your architecture docs. One plugin is listed in the bundle metadata.
- Session commit flow that writes learnings into AGENTS.md
- Cross-tool AI interoperability via shared agent instructions
- Installable skills catalog alignment with agent workflows
- Designed for repeatable updates after each session
- Workflow-oriented community plugin (single bundle entry)
Olshansk Agent Skills by the numbers
- Data as of Jul 28, 2026 (Skillselion catalog sync)
/plugin install olshansk-agent-skills@Olshansk/agent-skillsAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 8 |
|---|---|
| Last updated | July 27, 2026 |
| Repository | Olshansk/agent-skills ↗ |
What it does
Capture what each coding session taught the agent and persist it to AGENTS.md so Claude Code, Cursor, and other tools share the same rules and skills catalog.
Who is it for?
Best when you're maintaining AGENTS.md and a skills catalog and want a structured end-of-session commit habit.
Skip if: Skip if you forbid AGENTS.md or want full persistent memory graphs instead of markdown governance.
What you get
After install, you can commit session outcomes to AGENTS.md so skills, rules, and updates stay portable across compatible agents.
- Updated AGENTS.md sections from session commit
- Aligned references to installable skills in the catalog
- Portable agent instructions for other compatible tools
Recommended Plugins
0pg Cc MarketplacePersonal Claude Code plugins collection
1shot Labs Squadron Comms PluginVoice communication system with ElevenLabs TTS for multi-agent coordination in Claude Code3
23blocks Os Ai MaestroAI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging.733
3commas Io Commas ClaudeThis is a repo with shared agents and skills used company-wide4
884js Agent Plugins1 plugin
A5c Ai BabysitterBabysitter enforces obedience to agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration1.6kHow it compares
AGENTS.md session-commit workflow, not a persistent memory MCP or marketplace-only catalog.
FAQ
Who is Olshansk Agent Skills for?
Developers using multiple AI coding tools who centralize instructions in AGENTS.md and want session learnings captured automatically.
When should I use Olshansk Agent Skills?
Use it at the end of sessions where you changed conventions, added skills, or fixed recurring agent mistakes worth documenting.
How do I add Olshansk Agent Skills to my agent?
Install the plugin from Olshansk/agent-skills in Claude Code, keep AGENTS.md in your repo root, and run the session commit workflow when closing work.