Updated 1d ago
by conorbronsdon
agent-context-os
Portable, evolving context and workflow layer that works across Claude Code, Codex, Hermes Agent, OpenClaw, Cursor, Devin and other compatible coding agents. All backed by Git.
29 GitHub stars (29)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 15 skills (15 skills found in its SKILL.md files)
- 10 forks (10 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add conorbronsdon/agent-context-os
Asks which skills and agents to install. Just one: npx skills add conorbronsdon/agent-context-os --skill contextos-workspace — add -g for every project.
Claude Code
git clone https://github.com/conorbronsdon/agent-context-oscp -r "agent-context-os/skills/contextos-workspace" ~/.claude/skills/
Copies the contextos-workspace skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add conorbronsdon/agent-context-os
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
contextos-workspace
Run Context OS continuity and lifecycle workflows in a user-selected Context OS workspace. Use when asked to inspect, set up, update, or close a Context OS session.
skills/contextos-workspace/SKILL.md on GitHub (opens in a new tab) -
context-end
Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety. Use only when the user explicitly asks to end, close, or hand off the current session.
.agents/skills/context-end/SKILL.md on GitHub (opens in a new tab) -
context-setup
Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review. Use only when the user explicitly asks to initialize or redo workspace context.
.agents/skills/context-setup/SKILL.md on GitHub (opens in a new tab) -
context-start
Load this workspace's current state, recent decisions, blockers, priorities, and session continuity, then give a concise briefing. Use only when the user explicitly asks to begin or resume a workspace session.
.agents/skills/context-start/SKILL.md on GitHub (opens in a new tab) -
context-update
Save a brief mid-session checkpoint to this workspace and update current state only when a priority or open thread changed. Use only when the user explicitly asks to checkpoint or save current progress.
.agents/skills/context-update/SKILL.md on GitHub (opens in a new tab) -
end
Close this context workspace through the canonical reviewed handoff workflow. Use only when the user explicitly invokes end.
.agents/skills/end/SKILL.md on GitHub (opens in a new tab) -
migrate-gemini
Migrate selected Gemini CLI instructions, commands, skills, hooks, and MCP configuration into this workspace with a dry run, review gates, and parity checks.
.agents/skills/migrate-gemini/SKILL.md on GitHub (opens in a new tab) -
mine-gemini-workflows
Discover repeated, validated Gemini CLI workflows from a user-selected session directory and turn approved candidates into portable skills and parity tests without exporting private reasoning.
.agents/skills/mine-gemini-workflows/SKILL.md on GitHub (opens in a new tab) -
setup
Initialize or refresh this context workspace through the canonical guided review. Use only when the user explicitly invokes setup.
.agents/skills/setup/SKILL.md on GitHub (opens in a new tab) -
start
Load this context workspace and produce the canonical session briefing. Use only when the user explicitly invokes start.
.agents/skills/start/SKILL.md on GitHub (opens in a new tab) -
update
Save a concise checkpoint through the canonical workspace update workflow. Use only when the user explicitly invokes update.
.agents/skills/update/SKILL.md on GitHub (opens in a new tab) -
skill-creator
Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it
.claude/skills/skill-creator/SKILL.md on GitHub (opens in a new tab) -
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Pairs with writing-voice for full voice alignment.
writing/skills/avoid-ai-writing/SKILL.md on GitHub (opens in a new tab) -
press-outreach
Draft a cold pitch email to a music blog, playlist curator, or press contact. Load artist-context.md and promotion-strategy.md before running. Use when asked to "pitch [outlet]," "draft an email to [curator/blog]," or "write a press pitch."
projects/example-musician/workflow-examples/press-outreach/SKILL.md on GitHub (opens in a new tab) -
social-post
Write a platform-native social media post for a music release, show announcement, or general artist content. Load artist-context.md and promotion-strategy.md before running. Use when asked to "write a caption," "write a post for [platform]," or "help me announce [thing]."
projects/example-musician/workflow-examples/social-post/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.