ai-memory-routing-install
Use this skill for any request to install, refresh, repair, inspect, or remove ai-memory's agent-facing routing: managed instruction snippets, Agent Skills, CLAUDE.md/AGENTS.md integration, or local/global skill roots. Trigger by semantic intent rather than exact wording.
How do I install this agent skill?
npx skills add https://github.com/akitaonrails/ai-memory --skill ai-memory-routing-installIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill facilitates the installation and maintenance of agent routing instructions and managed skills across various platforms. While it uses markers to safely scope its modifications, it establishes an indirect prompt injection surface by writing data from an external tool into core agent instruction files and implements persistent behavior by modifying global user configuration directories.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
ai-memory routing install
Use this skill when the user wants ai-memory's agent-facing routing instructions or managed Agent Skills installed, refreshed, repaired, or removed.
Tools in this cluster
memory_install_self_routingreturns the canonical markered instruction block, marker strings, filename hints, notes, and managed skill payloads for agents that cannot let the MCP server write the host filesystem directly. Passcompact: truewhen managed Agent Skills are installed or when refreshing a file that already uses the compact snippet.
Managed instruction marker
The always-loaded instruction block is owned by ai-memory only between these markers.
- Start marker:
<!-- ai-memory:start --> - End marker:
<!-- ai-memory:end -->
Refresh must replace the first complete marker-bounded block whose start and end delimiters appear alone on their own lines, preserving unrelated content before and after it. Ignore inline mentions of marker strings inside prose or code; they are not delimiters. If no complete line-delimited block exists, append the canonical block with one blank line of separation. Never edit unrelated instructions while refreshing ai-memory routing.
Managed skill marker
Every ai-memory-managed SKILL.md file contains this ownership marker.
<!-- ai-memory-managed: routing-skill -->
Installers and uninstallers should overwrite or remove same-name skill files only when that marker is present, unless the user supplied an explicit force option. If a same-name skill lacks the marker, skip it with an actionable message so user-authored skills are preserved.
Global Grok installs also write $GROK_HOME/rules/ai-memory-handoff.md (default ~/.grok/rules/ai-memory-handoff.md) with the ownership marker <!-- ai-memory-managed: grok-handoff-rule -->. Overwrite or uninstall that file only when the marker is present, unless the user supplied --force. Project-scope Grok skill installs leave that user rule alone.
Skill install targets
Managed skills are ordinary Agent Skills. Their relative file path is <skill>/SKILL.md, and the installer prepends the selected skill root.
Project-local targets:
.claude/skills/<skill>/SKILL.mdfor Claude-compatible installs..agents/skills/<skill>/SKILL.mdfor cross-client installs..grok/skills/<skill>/SKILL.mdfor Grok Build CLI installs..github/skills/<skill>/SKILL.mdfor GitHub Copilot CLI installs.
Global targets:
~/.claude/skills/<skill>/SKILL.mdfor Claude-compatible installs.~/.agents/skills/<skill>/SKILL.mdfor cross-client installs.$GROK_HOME/skills/<skill>/SKILL.mdfor Grok Build CLI installs (default:~/.grok/skills/<skill>/SKILL.md).$COPILOT_HOME/skills/<skill>/SKILL.mdfor GitHub Copilot CLI installs (default:~/.copilot/skills/<skill>/SKILL.md).
Use platform-aware path joining. Do not build paths by string concatenation.
Refresh guidance
For an agent-side refresh, call the install-routing tool (pass compact: true if the target file already uses the compact snippet or if managed Agent Skills handle detailed routing). Its returned target_hints are authoritative for skill roots: choose the right instruction filename from agent_filenames, write the markered block with the agent's file-edit tool, and write each managed skill file below the selected hint using its relative_path. When a hint is an array, install the skill under every listed root. Claude Code normally uses CLAUDE.md and .claude/skills; Codex, OpenCode, Cursor, Gemini CLI, and AGENTS-aware clients normally use AGENTS.md and .agents/skills; Antigravity uses AGENTS.md and .agents/skills in a project, with separate App/IDE and CLI roots globally; Grok Build CLI uses AGENTS.md and .grok/skills; GitHub Copilot CLI uses AGENTS.md and .github/skills unless the project says otherwise.
For a CLI refresh, prefer the canonical install command. The snippet and skills must be updated from the same core-owned assets so they do not drift.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/akitaonrails/ai-memory/ai-memory-routing-install">View ai-memory-routing-install on skillZs</a>