`GitAgent`, a git-native spec for portable AI agents

Agent behavior becomes repo files, so prompts, skills, and reviews fit normal Git flows. Useful if you want one agent definition to target multiple runtimes without rebuilding the stack each time.

[ KEY POINTS ]

An agent is defined by three files: agent.yaml, SOUL.md, and SKILL.md; setup is simple and diffable.
Exports target multiple runtimes including Claude Code, OpenAI Agents SDK, CrewAI, Google ADK, and LangChain, reducing framework lock-in.
Git-native workflow is the real pitch: versioning, branching, PR review, git diff, and git blame for agent behavior.
npx @open-gitagent/gitagent run -r <repo> -a claude runs an agent repo directly, so distribution and reuse look like normal code sharing.
Optional compliance commands such as GitAgent audit and validation in GitHub Actions hint at enterprise ambitions; for small teams, portability matters more.

Originalwww.gitagent.sh/Read original →

// related

#0001
#0001Agents & tools GeekNews3 hours ago
GitHub confirms 3,800 repositories compromised via malicious `VS Code` extension
60radar
A single developer workstation became the entry point. VS Code extension trust is now part of supply-chain security, so extension audits are worth doing now.
- About 3,800 internal repositories were affected after one employee installed a trojanized VS Code extension.
- GitHub’s current assessment limits exposure to internal repositories, but compromised developer endpoints can still leak secrets and code context.
- The extension was removed from VS Code Marketplace, infected endpoints were isolated, and incident response started immediately.
- Practical takeaway: review installed IDE extensions, publisher names, permissions, and disable unused tools before they become build-chain risk.
Source: news.hada.io/topic?id=29731Read original →
FIG-0011:1
60radar
FIG-0011:1
#0002
#0002Agents & tools Claude Code Releases3 hours ago
`Claude Code` `v2.1.146` tightens code review and background sessions
50radar
Claude CodeTerminal coding agent — automates code edits with Claude
Small release, but it removes several annoying agent-run failures. Windows, MCP pagination, and multi-agent env handling all get more reliable.
- /simplify is now /code-review with optional effort levels like high, making review intent clearer in repeatable workflows.
- MCP resources/list, resources/templates/list, and prompts/list no longer drop results after page 1. Tooling backed by large MCP servers becomes safer.
- Windows fixes cover pwsh launch failures, terminal strobing, NTFS junction cleanup, and GNOME paste behavior. Cross-platform CLI friction drops.
- CLAUDE_CODE_SUBAGENT_MODEL now reaches child processes in multi-agent sessions. Model routing gets less brittle for delegated coding runs.
- Auto-updater retries transient network failures, and large diff rendering is faster. Not flashy, but daily-use reliability improved.
Source: github.com/anthropics/claude-code/releases/tag/v2.1.146Read original →
FIG-0021:1
50radar
FIG-0021:1
#0003
#0003Agents & tools GeekNews5 hours ago
Google Cloud revamps agent development with `Antigravity 2.0`
70radar
AntigravityAgent dev tool — links local prototypes to cloud execution
Google is packaging local prototyping and cloud deployment into one agent stack. If Managed Agents API removes hosting glue, it is worth tracking now.
- Antigravity 2.0 and Managed Agents API are framed as an integrated dev kit, not separate demos.
- The flow targets local prototyping first, then managed cloud execution. Less custom orchestration if the API is usable.
- The available text is short, so pricing, lock-in, and runtime limits remain unknown. Treat it as watchlist, not migration trigger.
Source: news.hada.io/topic?id=29718Read original →
FIG-0031:1
70radar
FIG-0031:1

`GitAgent`, a git-native spec for portable AI agents

// related

GitHub confirms 3,800 repositories compromised via malicious `VS Code` extension

`Claude Code` `v2.1.146` tightens code review and background sessions

Google Cloud revamps agent development with `Antigravity 2.0`