DevAgentRadar → Repo Harness Rule Patch

Goal: update our repository's permanent harness instructions based on this release.

Update the file that tool actually reads. Do not dump everything into one file.

• Claude Code → CLAUDE.md plus .claude/ (skills, hooks, settings, agents, commands). It does not read AGENTS.md natively; start CLAUDE.md with @AGENTS.md.
• Codex, Copilot, Cursor, Factory Droid, Grok Build, Roo Code, Goose, OpenCode, Amp, Zed, Aider → AGENTS.md.
• Gemini CLI / Antigravity → GEMINI.md. AGENTS.md only if context.fileName is set.
• Cursor glob-scoped rules → .cursor/rules/*.mdc (plain .md is ignored), not a second constitution.
• Codex MCP → .codex/config.toml, not .mcp.json.
• Copilot extra instructions → .github/copilot-instructions.md; custom agents → .github/agents/.
• Windsurf → .windsurf/rules (do not assume AGENTS.md).
• Cline → .clinerules.
• Procedures → a skill (SKILL.md). Enforcement the model must not skip → a hook. Isolated roles → subagents.
• Do not fork the same rule into three tool files.

Context

Assistant: xAI Grok CLI (Grok Build) Proposal: Audit security updates in Synced from monorepo Summary: Synced from monorepo · Changes: · Classify clipboard delivery confidence · Add durable session update append · Scope the xAI session bearer to first-party memory embedding endpoints · Persist subagent outputs to disk and bound long-lived agent state · Add MiniSweAgent:bash for mi Primary source: https://github.com/xai-org/grok-build/commit/98c3b2438aa922fbbe6178a5c0a4c48f85edc8ce

Why it matters

Release: Synced from monorepo Detail: Synced from monorepo · Changes: · Classify clipboard delivery confidence · Add durable session update append · Scope the xAI session bearer to first-party memory embedding endpoints · Persist subagent outputs to disk and bound long-lived agent state · Add MiniSweAgent:bash for mini-swe-agent parity · Revert taking local sessions off the persistent shell · Contextual tip recommending grok wrap on S Themes: agent, mcp, model, security, cli Config surfaces changed: permission rules Developer angle: Try in a throwaway repo before changing daily workflow. Team angle: Pilot / sandbox / policy review before org rollout. Source: https://github.com/xai-org/grok-build/commit/98c3b2438aa922fbbe6178a5c0a4c48f85edc8ce

Suggested actions

1. Review the permission rules config for xAI Grok CLI (Grok Build) to verify the changes don't break your workflow.
2. Read the release notes for xAI Grok CLI (Grok Build) 98c3b24 to understand the full scope of the update.

Config surfaces this release may change

• permission rules (high confidence) — check your repo before applying

After you finish

Do not report this as applied to DevAgentRadar. You cannot write the visitor's loop.

Tell the human: open https://devagentradar.com/proposals/xai-grok-cli-98c3b24-audit-security-updates-in-synced-from-monorepo and mark Applied, Skipped, or Failed. Proposal id: f30286d4-586e-43f2-b62d-3dc33492587c

Instructions:

1. Read the existing context files and settings for the tools in this repo.
2. Draft an explicit Git diff. Update ONLY agent harness rules or tool configuration.
3. Call out deprecated flags, obsolete habits, or changed permission boundaries.
4. Do not touch application logic.

Start with the proposed diff and say which layer and which tool's file it belongs in.