agdi 2026.2.21 → 2026.3.24

package/skills/coding-agent/SKILL.md

@@ -3,7 +3,7 @@ name: coding-agent
 description: Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
 metadata:
   {
-    "openclaw": { "emoji": "🧩", "requires": { "anyBins": ["claude", "codex", "opencode", "pi"] } },
+    "agdi": { "emoji": "🧩", "requires": { "anyBins": ["claude", "codex", "opencode", "pi"] } },
   }
 ---
 
@@ -120,7 +120,7 @@ bash pty:true workdir:~/project background:true command:"codex --yolo 'Refactor
 
 ### Reviewing PRs
 
-**⚠️ CRITICAL: Never review PRs in OpenClaw's own project folder!**
+**⚠️ CRITICAL: Never review PRs in Agdi's own project folder!**
 Clone to temp folder or use git worktree.
 
 ```bash
@@ -232,7 +232,7 @@ git worktree remove /tmp/issue-99
 6. **vanilla for reviewing** - no special flags needed
 7. **Parallel is OK** - run many Codex processes at once for batch work
 8. **NEVER start Codex in ~/clawd/** - it'll read your soul docs and get weird ideas about the org chart!
-9. **NEVER checkout branches in ~/Projects/openclaw/** - that's the LIVE OpenClaw instance!
+9. **NEVER checkout branches in ~/Projects/agdi/** - that's the LIVE Agdi instance!
 
 ---
 
@@ -254,13 +254,13 @@ This prevents the user from seeing only "Agent failed before reply" and having n
 
 ## Auto-Notify on Completion
 
-For long-running background tasks, append a wake trigger to your prompt so OpenClaw gets notified immediately when the agent finishes (instead of waiting for the next heartbeat):
+For long-running background tasks, append a wake trigger to your prompt so Agdi gets notified immediately when the agent finishes (instead of waiting for the next heartbeat):
 
 ```
 ... your task here.
 
 When completely finished, run this command to notify me:
-openclaw system event --text "Done: [brief summary of what was built]" --mode now
+agdi system event --text "Done: [brief summary of what was built]" --mode now
 ```
 
 **Example:**
@@ -268,7 +268,7 @@ openclaw system event --text "Done: [brief summary of what was built]" --mode no
 ```bash
 bash pty:true workdir:~/project background:true command:"codex --yolo exec 'Build a REST API for todos.
 
-When completely finished, run: openclaw system event --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'"
+When completely finished, run: agdi system event --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'"
 ```
 
 This triggers an immediate wake event — Skippy gets pinged in seconds, not 10 minutes.

package/skills/discord/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: discord
 description: "Discord ops via the message tool (channel=discord)."
-metadata: { "openclaw": { "emoji": "🎮", "requires": { "config": ["channels.discord.token"] } } }
+metadata: { "agdi": { "emoji": "🎮", "requires": { "config": ["channels.discord.token"] } } }
 allowed-tools: ["message"]
 ---
 

package/skills/eightctl/SKILL.md

@@ -4,7 +4,7 @@ description: Control Eight Sleep pods (status, temperature, alarms, schedules).
 homepage: https://eightctl.sh
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🎛️",
         "requires": { "bins": ["eightctl"] },

package/skills/food-order/SKILL.md

@@ -2,7 +2,7 @@
 name: food-order
 description: Reorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA.
 homepage: https://ordercli.sh
-metadata: {"openclaw":{"emoji":"🥡","requires":{"bins":["ordercli"]},"install":[{"id":"go","kind":"go","module":"github.com/steipete/ordercli/cmd/ordercli@latest","bins":["ordercli"],"label":"Install ordercli (go)"}]}}
+metadata: {"agdi":{"emoji":"🥡","requires":{"bins":["ordercli"]},"install":[{"id":"go","kind":"go","module":"github.com/steipete/ordercli/cmd/ordercli@latest","bins":["ordercli"],"label":"Install ordercli (go)"}]}}
 ---
 
 # Food order (Foodora via ordercli)

package/skills/gemini/SKILL.md

@@ -4,7 +4,7 @@ description: Gemini CLI for one-shot Q&A, summaries, and generation.
 homepage: https://ai.google.dev/
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "♊️",
         "requires": { "bins": ["gemini"] },

package/skills/gifgrep/SKILL.md

@@ -4,7 +4,7 @@ description: Search GIF providers with CLI/TUI, download results, and extract st
 homepage: https://gifgrep.com
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🧲",
         "requires": { "bins": ["gifgrep"] },

package/skills/github/SKILL.md

@@ -3,7 +3,7 @@ name: github
 description: "Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries."
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🐙",
         "requires": { "bins": ["gh"] },

package/skills/gog/SKILL.md

@@ -4,7 +4,7 @@ description: Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets,
 homepage: https://gogcli.sh
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🎮",
         "requires": { "bins": ["gog"] },

package/skills/goplaces/SKILL.md

@@ -4,7 +4,7 @@ description: Query Google Places API (New) via the goplaces CLI for text search,
 homepage: https://github.com/steipete/goplaces
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📍",
         "requires": { "bins": ["goplaces"], "env": ["GOOGLE_PLACES_API_KEY"] },

package/skills/healthcheck/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: healthcheck
-description: Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
+description: Host security hardening and risk-tolerance configuration for Agdi deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, Agdi cron scheduling for periodic checks, or version status checks on a machine running Agdi (laptop, workstation, Pi, VPS).
 ---
 
-# OpenClaw Host Hardening
+# Agdi Host Hardening
 
 ## Overview
 
-Assess and harden the host running OpenClaw, then align it to a user-defined risk tolerance without breaking access. Use OpenClaw security tooling as a first-class signal, but treat OS hardening as a separate, explicit set of steps.
+Assess and harden the host running Agdi, then align it to a user-defined risk tolerance without breaking access. Use Agdi security tooling as a first-class signal, but treat OS hardening as a separate, explicit set of steps.
 
 ## Core rules
 
@@ -15,7 +15,7 @@ Assess and harden the host running OpenClaw, then align it to a user-defined ris
 - Require explicit approval before any state-changing action.
 - Do not modify remote access settings without confirming how the user connects.
 - Prefer reversible, staged changes with a rollback plan.
-- Never claim OpenClaw changes the host firewall, SSH, or OS updates; it does not.
+- Never claim Agdi changes the host firewall, SSH, or OS updates; it does not.
 - If role/identity is unknown, provide recommendations only.
 - Formatting: every set of user choices must be numbered so the user can reply with a single digit.
 - System-level backups are recommended; try to verify status.
@@ -36,12 +36,12 @@ Determine (in order):
 2. Privilege level (root/admin vs user).
 3. Access path (local console, SSH, RDP, tailnet).
 4. Network exposure (public IP, reverse proxy, tunnel).
-5. OpenClaw gateway status and bind address.
+5. Agdi gateway status and bind address.
 6. Backup system and status (e.g., Time Machine, system images, snapshots).
 7. Deployment context (local mac app, headless gateway host, remote gateway, container/CI).
 8. Disk encryption status (FileVault/LUKS/BitLocker).
 9. OS automatic security updates status.
-   Note: these are not blocking items, but are highly recommended, especially if OpenClaw can access sensitive data.
+   Note: these are not blocking items, but are highly recommended, especially if Agdi can access sensitive data.
 10. Usage mode for a personal assistant with full access (local workstation vs headless/remote vs other).
 
 First ask once for permission to run read-only checks. If granted, run them by default and only ask questions for items you cannot infer or verify. Do not ask for information already visible in runtime or command output. Keep the permission ask as a single sentence, and list follow-up info needed as an unordered list (not numbered) unless you are presenting selectable choices.
@@ -74,24 +74,24 @@ If the user grants read-only permission, run the OS-appropriate checks by defaul
    - macOS: `/usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate` and `pfctl -s info`.
 4. Backups (macOS): `tmutil status` (if Time Machine is used).
 
-### 2) Run OpenClaw security audits (read-only)
+### 2) Run Agdi security audits (read-only)
 
-As part of the default read-only checks, run `openclaw security audit --deep`. Only offer alternatives if the user requests them:
+As part of the default read-only checks, run `agdi security audit --deep`. Only offer alternatives if the user requests them:
 
-1. `openclaw security audit` (faster, non-probing)
-2. `openclaw security audit --json` (structured output)
+1. `agdi security audit` (faster, non-probing)
+2. `agdi security audit --json` (structured output)
 
-Offer to apply OpenClaw safe defaults (numbered):
+Offer to apply Agdi safe defaults (numbered):
 
-1. `openclaw security audit --fix`
+1. `agdi security audit --fix`
 
-Be explicit that `--fix` only tightens OpenClaw defaults and file permissions. It does not change host firewall, SSH, or OS update policies.
+Be explicit that `--fix` only tightens Agdi defaults and file permissions. It does not change host firewall, SSH, or OS update policies.
 
 If browser control is enabled, recommend that 2FA be enabled on all important accounts, with hardware keys preferred and SMS not sufficient.
 
-### 3) Check OpenClaw version/update status (read-only)
+### 3) Check Agdi version/update status (read-only)
 
-As part of the default read-only checks, run `openclaw update status`.
+As part of the default read-only checks, run `agdi update status`.
 
 Report the current channel and whether an update is available.
 
@@ -117,7 +117,7 @@ Provide a plan that includes:
 - Access-preservation strategy and rollback
 - Risks and potential lockout scenarios
 - Least-privilege notes (e.g., avoid admin usage, tighten ownership/permissions where safe)
-- Credential hygiene notes (location of OpenClaw creds, prefer disk encryption)
+- Credential hygiene notes (location of Agdi creds, prefer disk encryption)
 
 Always show the plan before any changes.
 
@@ -146,7 +146,7 @@ Re-check:
 - Firewall status
 - Listening ports
 - Remote access still works
-- OpenClaw security audit (re-run)
+- Agdi security audit (re-run)
 
 Deliver a final posture report and note any deferred items.
 
@@ -168,50 +168,50 @@ If unsure, ask.
 
 ## Periodic checks
 
-After OpenClaw install or first hardening pass, run at least one baseline audit and version check:
+After Agdi install or first hardening pass, run at least one baseline audit and version check:
 
-- `openclaw security audit`
-- `openclaw security audit --deep`
-- `openclaw update status`
+- `agdi security audit`
+- `agdi security audit --deep`
+- `agdi update status`
 
-Ongoing monitoring is recommended. Use the OpenClaw cron tool/CLI to schedule periodic audits (Gateway scheduler). Do not create scheduled tasks without explicit approval. Store outputs in a user-approved location and avoid secrets in logs.
+Ongoing monitoring is recommended. Use the Agdi cron tool/CLI to schedule periodic audits (Gateway scheduler). Do not create scheduled tasks without explicit approval. Store outputs in a user-approved location and avoid secrets in logs.
 When scheduling headless cron runs, include a note in the output that instructs the user to call `healthcheck` so issues can be fixed.
 
 ### Required prompt to schedule (always)
 
 After any audit or hardening pass, explicitly offer scheduling and require a direct response. Use a short prompt like (numbered):
 
-1. “Do you want me to schedule periodic audits (e.g., daily/weekly) via `openclaw cron add`?”
+1. “Do you want me to schedule periodic audits (e.g., daily/weekly) via `agdi cron add`?”
 
 If the user says yes, ask for:
 
 - cadence (daily/weekly), preferred time window, and output location
-- whether to also schedule `openclaw update status`
+- whether to also schedule `agdi update status`
 
 Use a stable cron job name so updates are deterministic. Prefer exact names:
 
 - `healthcheck:security-audit`
 - `healthcheck:update-status`
 
-Before creating, `openclaw cron list` and match on exact `name`. If found, `openclaw cron edit <id> ...`.
-If not found, `openclaw cron add --name <name> ...`.
+Before creating, `agdi cron list` and match on exact `name`. If found, `agdi cron edit <id> ...`.
+If not found, `agdi cron add --name <name> ...`.
 
 Also offer a periodic version check so the user can decide when to update (numbered):
 
-1. `openclaw update status` (preferred for source checkouts and channels)
-2. `npm view openclaw version` (published npm version)
+1. `agdi update status` (preferred for source checkouts and channels)
+2. `npm view agdi version` (published npm version)
 
-## OpenClaw command accuracy
+## Agdi command accuracy
 
 Use only supported commands and flags:
 
-- `openclaw security audit [--deep] [--fix] [--json]`
-- `openclaw status` / `openclaw status --deep`
-- `openclaw health --json`
-- `openclaw update status`
-- `openclaw cron add|list|runs|run`
+- `agdi security audit [--deep] [--fix] [--json]`
+- `agdi status` / `agdi status --deep`
+- `agdi health --json`
+- `agdi update status`
+- `agdi cron add|list|runs|run`
 
-Do not invent CLI flags or imply OpenClaw enforces host firewall/SSH policies.
+Do not invent CLI flags or imply Agdi enforces host firewall/SSH policies.
 
 ## Logging and audit trail
 
@@ -230,7 +230,7 @@ Only write to memory files when the user explicitly opts in and the session is a
 (per `docs/reference/templates/AGENTS.md`). Otherwise provide a redacted, paste-ready summary the user can
 decide to save elsewhere.
 
-Follow the durable-memory prompt format used by OpenClaw compaction:
+Follow the durable-memory prompt format used by Agdi compaction:
 
 - Write lasting notes to `memory/YYYY-MM-DD.md`.
 

package/skills/himalaya/SKILL.md

@@ -4,7 +4,7 @@ description: "CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read,
 homepage: https://github.com/pimalaya/himalaya
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📧",
         "requires": { "bins": ["himalaya"] },

package/skills/imsg/SKILL.md

@@ -4,7 +4,7 @@ description: iMessage/SMS CLI for listing chats, history, watch, and sending.
 homepage: https://imsg.to
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📨",
         "os": ["darwin"],

package/skills/mcporter/SKILL.md

@@ -4,7 +4,7 @@ description: Use the mcporter CLI to list, configure, auth, and call MCP servers
 homepage: http://mcporter.dev
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📦",
         "requires": { "bins": ["mcporter"] },

package/skills/model-usage/SKILL.md

@@ -3,7 +3,7 @@ name: model-usage
 description: Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📊",
         "os": ["darwin"],

package/skills/nano-banana-pro/SKILL.md

@@ -4,7 +4,7 @@ description: Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
 homepage: https://ai.google.dev/
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🍌",
         "requires": { "bins": ["uv"], "env": ["GEMINI_API_KEY"] },
@@ -48,11 +48,11 @@ uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scen
 API key
 
 - `GEMINI_API_KEY` env var
-- Or set `skills."nano-banana-pro".apiKey` / `skills."nano-banana-pro".env.GEMINI_API_KEY` in `~/.openclaw/openclaw.json`
+- Or set `skills."nano-banana-pro".apiKey` / `skills."nano-banana-pro".env.GEMINI_API_KEY` in `~/.agdi/agdi.json`
 
 Notes
 
 - Resolutions: `1K` (default), `2K`, `4K`.
 - Use timestamps in filenames: `yyyy-mm-dd-hh-mm-ss-name.png`.
-- The script prints a `MEDIA:` line for OpenClaw to auto-attach on supported chat providers.
+- The script prints a `MEDIA:` line for Agdi to auto-attach on supported chat providers.
 - Do not read the image back; report the saved path only.

package/skills/nano-pdf/SKILL.md

@@ -4,7 +4,7 @@ description: Edit PDFs with natural-language instructions using the nano-pdf CLI
 homepage: https://pypi.org/project/nano-pdf/
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "📄",
         "requires": { "bins": ["nano-pdf"] },

package/skills/notion/SKILL.md

@@ -4,7 +4,7 @@ description: Notion API for creating and managing pages, databases, and blocks.
 homepage: https://developers.notion.com
 metadata:
   {
-    "openclaw":
+    "agdi":
       { "emoji": "📝", "requires": { "env": ["NOTION_API_KEY"] }, "primaryEnv": "NOTION_API_KEY" },
   }
 ---

package/skills/obsidian/SKILL.md

@@ -4,7 +4,7 @@ description: Work with Obsidian vaults (plain Markdown notes) and automate via o
 homepage: https://help.obsidian.md
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "💎",
         "requires": { "bins": ["obsidian-cli"] },

package/skills/openai-image-gen/SKILL.md

@@ -4,7 +4,7 @@ description: Batch-generate images via OpenAI Images API. Random prompt sampler
 homepage: https://platform.openai.com/docs/api-reference/images
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🖼️",
         "requires": { "bins": ["python3"], "env": ["OPENAI_API_KEY"] },

package/skills/openai-whisper/SKILL.md

@@ -4,7 +4,7 @@ description: Local speech-to-text with the Whisper CLI (no API key).
 homepage: https://openai.com/research/whisper
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🎙️",
         "requires": { "bins": ["whisper"] },

package/skills/openai-whisper-api/SKILL.md

@@ -4,7 +4,7 @@ description: Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
 homepage: https://platform.openai.com/docs/guides/speech-to-text
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "☁️",
         "requires": { "bins": ["curl"], "env": ["OPENAI_API_KEY"] },
@@ -39,7 +39,7 @@ Defaults:
 
 ## API key
 
-Set `OPENAI_API_KEY`, or configure it in `~/.openclaw/openclaw.json`:
+Set `OPENAI_API_KEY`, or configure it in `~/.agdi/agdi.json`:
 
 ```json5
 {

package/skills/openhue/SKILL.md

@@ -4,7 +4,7 @@ description: Control Philips Hue lights/scenes via the OpenHue CLI.
 homepage: https://www.openhue.io/cli
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "💡",
         "requires": { "bins": ["openhue"] },

package/skills/oracle/SKILL.md

@@ -4,7 +4,7 @@ description: Best practices for using the oracle CLI (prompt + file bundling, en
 homepage: https://askoracle.dev
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🧿",
         "requires": { "bins": ["oracle"] },

package/skills/ordercli/SKILL.md

@@ -4,7 +4,7 @@ description: Foodora-only CLI for checking past orders and active order status (
 homepage: https://ordercli.sh
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🛵",
         "requires": { "bins": ["ordercli"] },

package/skills/peekaboo/SKILL.md

@@ -4,7 +4,7 @@ description: Capture and automate macOS UI with the Peekaboo CLI.
 homepage: https://peekaboo.boo
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "👀",
         "os": ["darwin"],

package/skills/sag/SKILL.md

@@ -4,7 +4,7 @@ description: ElevenLabs text-to-speech with mac-style say UX.
 homepage: https://sag.sh
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🗣️",
         "requires": { "bins": ["sag"], "env": ["ELEVENLABS_API_KEY"] },

package/skills/session-logs/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: session-logs
 description: Search and analyze your own session logs (older/parent conversations) using jq.
-metadata: { "openclaw": { "emoji": "📜", "requires": { "bins": ["jq", "rg"] } } }
+metadata: { "agdi": { "emoji": "📜", "requires": { "bins": ["jq", "rg"] } } }
 ---
 
 # session-logs
@@ -14,7 +14,7 @@ Use this skill when the user asks about prior chats, parent conversations, or hi
 
 ## Location
 
-Session logs live at: `~/.openclaw/agents/<agentId>/sessions/` (use the `agent=<id>` value from the system prompt Runtime line).
+Session logs live at: `~/.agdi/agents/<agentId>/sessions/` (use the `agent=<id>` value from the system prompt Runtime line).
 
 - **`sessions.json`** - Index mapping session keys to session IDs
 - **`<session-id>.jsonl`** - Full conversation transcript per session
@@ -34,7 +34,7 @@ Each `.jsonl` file contains messages with:
 ### List all sessions by date and size
 
 ```bash
-for f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
+for f in ~/.agdi/agents/<agentId>/sessions/*.jsonl; do
   date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
   size=$(ls -lh "$f" | awk '{print $5}')
   echo "$date $size $(basename $f)"
@@ -44,7 +44,7 @@ done | sort -r
 ### Find sessions from a specific day
 
 ```bash
-for f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
+for f in ~/.agdi/agents/<agentId>/sessions/*.jsonl; do
   head -1 "$f" | jq -r '.timestamp' | grep -q "2026-01-06" && echo "$f"
 done
 ```
@@ -70,7 +70,7 @@ jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
 ### Daily cost summary
 
 ```bash
-for f in ~/.openclaw/agents/<agentId>/sessions/*.jsonl; do
+for f in ~/.agdi/agents/<agentId>/sessions/*.jsonl; do
   date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
   cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' "$f")
   echo "$date $cost"
@@ -98,7 +98,7 @@ jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.json
 ### Search across ALL sessions for a phrase
 
 ```bash
-rg -l "phrase" ~/.openclaw/agents/<agentId>/sessions/*.jsonl
+rg -l "phrase" ~/.agdi/agents/<agentId>/sessions/*.jsonl
 ```
 
 ## Tips
@@ -111,5 +111,5 @@ rg -l "phrase" ~/.openclaw/agents/<agentId>/sessions/*.jsonl
 ## Fast text-only hint (low noise)
 
 ```bash
-jq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' ~/.openclaw/agents/<agentId>/sessions/<id>.jsonl | rg 'keyword'
+jq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' ~/.agdi/agents/<agentId>/sessions/<id>.jsonl | rg 'keyword'
 ```

package/skills/sherpa-onnx-tts/SKILL.md

@@ -3,7 +3,7 @@ name: sherpa-onnx-tts
 description: Local text-to-speech via sherpa-onnx (offline, no cloud)
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🗣️",
         "os": ["darwin", "linux", "win32"],
@@ -63,10 +63,10 @@ Local TTS using the sherpa-onnx offline CLI.
 
 ## Install
 
-1. Download the runtime for your OS (extracts into `~/.openclaw/tools/sherpa-onnx-tts/runtime`)
-2. Download a voice model (extracts into `~/.openclaw/tools/sherpa-onnx-tts/models`)
+1. Download the runtime for your OS (extracts into `~/.agdi/tools/sherpa-onnx-tts/runtime`)
+2. Download a voice model (extracts into `~/.agdi/tools/sherpa-onnx-tts/models`)
 
-Update `~/.openclaw/openclaw.json`:
+Update `~/.agdi/agdi.json`:
 
 ```json5
 {
@@ -74,8 +74,8 @@ Update `~/.openclaw/openclaw.json`:
     entries: {
       "sherpa-onnx-tts": {
         env: {
-          SHERPA_ONNX_RUNTIME_DIR: "~/.openclaw/tools/sherpa-onnx-tts/runtime",
-          SHERPA_ONNX_MODEL_DIR: "~/.openclaw/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high",
+          SHERPA_ONNX_RUNTIME_DIR: "~/.agdi/tools/sherpa-onnx-tts/runtime",
+          SHERPA_ONNX_MODEL_DIR: "~/.agdi/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high",
         },
       },
     },

package/skills/slack/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: slack
-description: Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
-metadata: { "openclaw": { "emoji": "💬", "requires": { "config": ["channels.slack"] } } }
+description: Use when you need to control Slack from Agdi via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
+metadata: { "agdi": { "emoji": "💬", "requires": { "config": ["channels.slack"] } } }
 ---
 
 # Slack Actions
 
 ## Overview
 
-Use `slack` to react, manage pins, send/edit/delete messages, and fetch member info. The tool uses the bot token configured for OpenClaw.
+Use `slack` to react, manage pins, send/edit/delete messages, and fetch member info. The tool uses the bot token configured for Agdi.
 
 ## Inputs to collect
 
@@ -57,7 +57,7 @@ Message context lines include `slack message id` and `channel` fields you can re
 {
   "action": "sendMessage",
   "to": "channel:C123",
-  "content": "Hello from OpenClaw"
+  "content": "Hello from Agdi"
 }
 ```
 

package/skills/songsee/SKILL.md

@@ -4,7 +4,7 @@ description: Generate spectrograms and feature-panel visualizations from audio w
 homepage: https://github.com/steipete/songsee
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🌊",
         "requires": { "bins": ["songsee"] },

package/skills/sonoscli/SKILL.md

@@ -4,7 +4,7 @@ description: Control Sonos speakers (discover/status/play/volume/group).
 homepage: https://sonoscli.sh
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🔊",
         "requires": { "bins": ["sonos"] },

package/skills/spotify-player/SKILL.md

@@ -4,7 +4,7 @@ description: Terminal Spotify playback/search via spogo (preferred) or spotify_p
 homepage: https://www.spotify.com
 metadata:
   {
-    "openclaw":
+    "agdi":
       {
         "emoji": "🎵",
         "requires": { "anyBins": ["spogo", "spotify_player"] },