@intent-systems/nexus 2026.1.5-3

package/skills/bear-notes/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: bear-notes
+description: Create, search, and manage Bear notes via grizzly CLI.
+homepage: https://bear.app
+metadata: {"nexus":{"emoji":"🐻","os":["darwin"],"requires":{"bins":["grizzly"]},"install":[{"id":"go","kind":"go","module":"github.com/tylerwince/grizzly/cmd/grizzly@latest","bins":["grizzly"],"label":"Install grizzly (go)"}]}}
+---
+
+# Bear Notes
+
+Use `grizzly` to create, read, and manage notes in Bear on macOS.
+
+Requirements
+- Bear app installed and running
+- For some operations (add-text, tags, open-note --selected), a Bear app token (stored in `~/.config/grizzly/token`)
+
+## Getting a Bear Token
+
+For operations that require a token (add-text, tags, open-note --selected), you need an authentication token:
+1. Open Bear → Help → API Token → Copy Token
+2. Save it: `echo "YOUR_TOKEN" > ~/.config/grizzly/token`
+
+## Common Commands
+
+Create a note
+```bash
+echo "Note content here" | grizzly create --title "My Note" --tag work
+grizzly create --title "Quick Note" --tag inbox < /dev/null
+```
+
+Open/read a note by ID
+```bash
+grizzly open-note --id "NOTE_ID" --enable-callback --json
+```
+
+Append text to a note
+```bash
+echo "Additional content" | grizzly add-text --id "NOTE_ID" --mode append --token-file ~/.config/grizzly/token
+```
+
+List all tags
+```bash
+grizzly tags --enable-callback --json --token-file ~/.config/grizzly/token
+```
+
+Search notes (via open-tag)
+```bash
+grizzly open-tag --name "work" --enable-callback --json
+```
+
+## Options
+
+Common flags:
+- `--dry-run` — Preview the URL without executing
+- `--print-url` — Show the x-callback-url
+- `--enable-callback` — Wait for Bear's response (needed for reading data)
+- `--json` — Output as JSON (when using callbacks)
+- `--token-file PATH` — Path to Bear API token file
+
+## Configuration
+
+Grizzly reads config from (in priority order):
+1. CLI flags
+2. Environment variables (`GRIZZLY_TOKEN_FILE`, `GRIZZLY_CALLBACK_URL`, `GRIZZLY_TIMEOUT`)
+3. `.grizzly.toml` in current directory
+4. `~/.config/grizzly/config.toml`
+
+Example `~/.config/grizzly/config.toml`:
+```toml
+token_file = "~/.config/grizzly/token"
+callback_url = "http://127.0.0.1:42123/success"
+timeout = "5s"
+```
+
+## Notes
+
+- Bear must be running for commands to work
+- Note IDs are Bear's internal identifiers (visible in note info or via callbacks)
+- Use `--enable-callback` when you need to read data back from Bear
+- Some operations require a valid token (add-text, tags, open-note --selected)

package/skills/bird/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: bird
+description: X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.
+homepage: https://bird.fast
+metadata: {"nexus":{"emoji":"🐦","requires":{"bins":["bird"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/bird","bins":["bird"],"label":"Install bird (brew)"}]}}
+---
+
+# bird
+
+Use `bird` to read/search X and post tweets/replies.
+
+## Docs
+
+- `docs/auth.md`
+- `docs/troubleshooting.md`
+
+Quick start
+- `bird check`
+- `bird whoami`
+- `bird read <url-or-id>`
+- `bird thread <url-or-id>`
+- `bird search "query" -n 5`
+- `bird timeline -n 10`
+
+Posting (confirm with user first)
+- `bird tweet "text"`
+- `bird reply <id-or-url> "text"`
+
+Auth sources
+- Browser cookies (default: Firefox/Chrome)
+- Sweetistics API: set `SWEETISTICS_API_KEY` or use `--engine sweetistics`
+- Check sources: `bird check`

package/skills/bird/docs/auth.md

@@ -0,0 +1,31 @@
+# bird Authentication
+
+bird can authenticate via browser cookies (free) or Sweetistics (API key).
+
+## Option 1: Browser cookies (recommended)
+
+1. Log into X in Chrome or Firefox.
+2. Run:
+
+```bash
+bird check
+bird whoami
+```
+
+`bird check` should show Chrome/Firefox cookies as available.
+
+## Option 2: Sweetistics API
+
+If cookies are unavailable or unreliable:
+
+```bash
+export SWEETISTICS_API_KEY="your-api-key"
+bird --engine sweetistics whoami
+```
+
+Persist in your shell profile if desired.
+
+## Notes
+
+- Cookie auth reads your browser session; it does not store passwords.
+- If cookies expire, just log in again and re-run `bird check`.

package/skills/bird/docs/troubleshooting.md

@@ -0,0 +1,31 @@
+# bird Troubleshooting
+
+## No authentication sources available
+
+**Symptom:** `bird check` shows no available auth.
+
+**Fix:**
+1. Log into X in Chrome or Firefox.
+2. Re-run `bird check`.
+3. Or use Sweetistics:
+
+```bash
+export SWEETISTICS_API_KEY="your-api-key"
+bird --engine sweetistics check
+```
+
+## Cookie expired
+
+**Symptom:** commands fail with auth errors.
+
+**Fix:** log out and back in to X in your browser, then retry.
+
+## Rate limiting
+
+**Symptom:** "rate limit exceeded".
+
+**Fix:** wait a bit or add a delay between requests:
+
+```bash
+bird search "query" --delay 2000
+```

package/skills/blogwatcher/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: blogwatcher
+description: Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
+homepage: https://github.com/Hyaxia/blogwatcher
+metadata: {"nexus":{"emoji":"📰","requires":{"bins":["blogwatcher"]},"install":[{"id":"go","kind":"go","module":"github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest","bins":["blogwatcher"],"label":"Install blogwatcher (go)"}]}}
+---
+
+# blogwatcher
+
+Track blog and RSS/Atom feed updates with the `blogwatcher` CLI.
+
+Install
+- Go: `go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest`
+
+Quick start
+- `blogwatcher --help`
+
+Common commands
+- Add a blog: `blogwatcher add "My Blog" https://example.com`
+- List blogs: `blogwatcher blogs`
+- Scan for updates: `blogwatcher scan`
+- List articles: `blogwatcher articles`
+- Mark an article read: `blogwatcher read 1`
+- Mark all articles read: `blogwatcher read-all`
+- Remove a blog: `blogwatcher remove "My Blog"`
+
+Example output
+```
+$ blogwatcher blogs
+Tracked blogs (1):
+
+  xkcd
+    URL: https://xkcd.com
+```
+```
+$ blogwatcher scan
+Scanning 1 blog(s)...
+
+  xkcd
+    Source: RSS | Found: 4 | New: 4
+
+Found 4 new article(s) total!
+```
+
+Notes
+- Use `blogwatcher <command> --help` to discover flags and options.

package/skills/blucli/SKILL.md

@@ -0,0 +1,27 @@
+---
+name: blucli
+description: BluOS CLI (blu) for discovery, playback, grouping, and volume.
+homepage: https://blucli.sh
+metadata: {"nexus":{"emoji":"🫐","requires":{"bins":["blu"]},"install":[{"id":"go","kind":"go","module":"github.com/steipete/blucli/cmd/blu@latest","bins":["blu"],"label":"Install blucli (go)"}]}}
+---
+
+# blucli (blu)
+
+Use `blu` to control Bluesound/NAD players.
+
+Quick start
+- `blu devices` (pick target)
+- `blu --device <id> status`
+- `blu play|pause|stop`
+- `blu volume set 15`
+
+Target selection (in priority order)
+- `--device <id|name|alias>`
+- `BLU_DEVICE`
+- config default (if set)
+
+Common tasks
+- Grouping: `blu group status|add|remove`
+- TuneIn search/play: `blu tunein search "query"`, `blu tunein play "query"`
+
+Prefer `--json` for scripts. Confirm the target device before changing playback.

package/skills/brave-search/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: brave-search
+description: Web search and content extraction via Brave Search API.
+homepage: https://brave.com/search/api
+metadata: {"nexus":{"emoji":"🦁","type":"connector","provides":["news","web-search"],"requires":{"bins":["node"],"env":["BRAVE_API_KEY"],"credentials":["brave-search"]},"primaryEnv":"BRAVE_API_KEY"}}
+---
+
+# Brave Search
+
+Headless web search (and lightweight content extraction) using Brave Search API. No browser required.
+
+## Docs
+
+- `docs/setup.md`
+- `docs/usage.md`
+- `docs/troubleshooting.md`
+
+## Search
+
+```bash
+node {baseDir}/scripts/search.mjs "query"
+node {baseDir}/scripts/search.mjs "query" -n 10
+node {baseDir}/scripts/search.mjs "query" --content
+node {baseDir}/scripts/search.mjs "query" -n 3 --content
+```
+
+## Extract a page
+
+```bash
+node {baseDir}/scripts/content.mjs "https://example.com/article"
+```
+
+Notes:
+- Needs `BRAVE_API_KEY`.
+- Content extraction is best-effort (good for articles; not for app-like sites).
+- If a site is blocked or too JS-heavy, prefer the `summarize` skill (it can use a Firecrawl fallback).

package/skills/brave-search/docs/setup.md

@@ -0,0 +1,40 @@
+# Brave Search Setup
+
+This connector uses the Brave Search API.
+
+## Prerequisites
+
+- Node.js available (`node --version`)
+- Brave Search API key (`BRAVE_API_KEY`)
+
+## Get an API key
+
+1. Visit https://brave.com/search/api/
+2. Create an API key (free tier is 2,000 queries/month)
+
+Store in 1Password (recommended):
+
+```bash
+op item create \
+  --category "API Credential" \
+  --title "Brave Search API Key" \
+  --vault Personal \
+  "credential[password]=YOUR_API_KEY_HERE"
+
+echo 'export BRAVE_API_KEY="op://Personal/Brave Search API Key/credential"' >> ~/.zshrc
+echo 'eval "$(op plugin run -- zsh)"' >> ~/.zshrc
+source ~/.zshrc
+```
+
+Or set directly:
+
+```bash
+export BRAVE_API_KEY="your-key-here"
+```
+
+## Verify
+
+```bash
+echo $BRAVE_API_KEY | grep -q . && echo "API key set"
+node {baseDir}/scripts/search.mjs "test query" -n 3
+```

package/skills/brave-search/docs/troubleshooting.md

@@ -0,0 +1,37 @@
+# Brave Search Troubleshooting
+
+## BRAVE_API_KEY not set
+
+```bash
+export BRAVE_API_KEY=$(op read "op://Personal/Brave Search API Key/credential")
+```
+
+## Rate limit exceeded
+
+Free tier allows 2,000 queries/month. Consider caching results:
+
+```bash
+CACHE_DIR="/tmp/brave-search-cache"
+mkdir -p "$CACHE_DIR"
+QUERY="your query"
+CACHE_FILE="$CACHE_DIR/$(echo "$QUERY" | md5).json"
+
+if [ -f "$CACHE_FILE" ]; then
+  cat "$CACHE_FILE"
+else
+  node {baseDir}/scripts/search.mjs "$QUERY" | tee "$CACHE_FILE"
+fi
+```
+
+## Content extraction is empty
+
+- Try a different URL (article vs app-like site).
+- Use `summarize` or `computer-use` for JS-heavy sites.
+
+## Cannot find module / script
+
+Run from the skill directory or use absolute paths:
+
+```bash
+node {baseDir}/scripts/search.mjs "test"
+```

package/skills/brave-search/docs/usage.md

@@ -0,0 +1,28 @@
+# Brave Search Usage
+
+## Search
+
+```bash
+node {baseDir}/scripts/search.mjs "query"
+node {baseDir}/scripts/search.mjs "query" -n 10
+node {baseDir}/scripts/search.mjs "query" --content
+node {baseDir}/scripts/search.mjs "query" -n 3 --content
+```
+
+## Extract a page
+
+```bash
+node {baseDir}/scripts/content.mjs "https://example.com/article"
+```
+
+## Parse results with jq
+
+```bash
+node {baseDir}/scripts/search.mjs "topic" | jq -r '.web.results[].url'
+node {baseDir}/scripts/search.mjs "topic" | jq -r '.web.results[] | "\(.title): \(.url)"'
+```
+
+## Notes
+
+- Content extraction is best-effort (good for articles; not for app-like sites).
+- For JS-heavy sites, consider `summarize` (Firecrawl fallback) or `computer-use`.

package/skills/brave-search/scripts/content.mjs

@@ -0,0 +1,53 @@
+#!/usr/bin/env node
+
+function usage() {
+  console.error(`Usage: content.mjs <url>`);
+  process.exit(2);
+}
+
+export async function fetchAsMarkdown(url) {
+  const resp = await fetch(url, {
+    headers: { "User-Agent": "nexus-brave-search/1.0" },
+  });
+  const html = await resp.text();
+
+  // Very lightweight “readability-ish” extraction without dependencies:
+  // - drop script/style/nav/footer
+  // - strip tags
+  // - keep paragraphs
+  const cleaned = html
+    .replace(/<script[\s\S]*?<\/script>/gi, " ")
+    .replace(/<style[\s\S]*?<\/style>/gi, " ")
+    .replace(/<(nav|footer|header)[\s\S]*?<\/\1>/gi, " ")
+    .replace(/<br\s*\/?>/gi, "\n")
+    .replace(/<\/p>/gi, "\n\n")
+    .replace(/<\/div>/gi, "\n")
+    .replace(/<[^>]+>/g, " ")
+    .replace(/&nbsp;/g, " ")
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/\s+\n/g, "\n")
+    .replace(/\n{3,}/g, "\n\n")
+    .replace(/[ \t]{2,}/g, " ")
+    .trim();
+
+  if (!resp.ok) {
+    return `> Fetch failed (${resp.status}).\n\n${cleaned.slice(0, 2000)}\n`;
+  }
+
+  const paras = cleaned
+    .split("\n\n")
+    .map((p) => p.trim())
+    .filter(Boolean)
+    .slice(0, 30);
+
+  return paras.map((p) => `- ${p}`).join("\n") + "\n";
+}
+
+const args = process.argv.slice(2);
+if (args.length === 0 || args[0] === "-h" || args[0] === "--help") usage();
+const url = args[0];
+process.stdout.write(await fetchAsMarkdown(url));

package/skills/brave-search/scripts/search.mjs

@@ -0,0 +1,79 @@
+#!/usr/bin/env node
+
+function usage() {
+  console.error(`Usage: search.mjs "query" [-n 5] [--content]`);
+  process.exit(2);
+}
+
+const args = process.argv.slice(2);
+if (args.length === 0 || args[0] === "-h" || args[0] === "--help") usage();
+
+const query = args[0];
+let n = 5;
+let withContent = false;
+
+for (let i = 1; i < args.length; i++) {
+  const a = args[i];
+  if (a === "-n") {
+    n = Number.parseInt(args[i + 1] ?? "5", 10);
+    i++;
+    continue;
+  }
+  if (a === "--content") {
+    withContent = true;
+    continue;
+  }
+  console.error(`Unknown arg: ${a}`);
+  usage();
+}
+
+const apiKey = (process.env.BRAVE_API_KEY ?? "").trim();
+if (!apiKey) {
+  console.error("Missing BRAVE_API_KEY");
+  process.exit(1);
+}
+
+const endpoint = new URL("https://api.search.brave.com/res/v1/web/search");
+endpoint.searchParams.set("q", query);
+endpoint.searchParams.set("count", String(Math.max(1, Math.min(n, 20))));
+endpoint.searchParams.set("text_decorations", "false");
+endpoint.searchParams.set("safesearch", "moderate");
+
+const resp = await fetch(endpoint, {
+  headers: {
+    Accept: "application/json",
+    "X-Subscription-Token": apiKey,
+  },
+});
+
+if (!resp.ok) {
+  const text = await resp.text().catch(() => "");
+  throw new Error(`Brave Search failed (${resp.status}): ${text}`);
+}
+
+const data = await resp.json();
+const results = (data?.web?.results ?? []).slice(0, n);
+
+const lines = [];
+for (const r of results) {
+  const title = String(r?.title ?? "").trim();
+  const url = String(r?.url ?? "").trim();
+  const desc = String(r?.description ?? "").trim();
+  if (!title || !url) continue;
+  lines.push(`- ${title}\n  ${url}${desc ? `\n  ${desc}` : ""}`);
+}
+
+process.stdout.write(lines.join("\n\n") + "\n");
+
+if (!withContent) process.exit(0);
+
+process.stdout.write("\n---\n\n");
+for (const r of results) {
+  const title = String(r?.title ?? "").trim();
+  const url = String(r?.url ?? "").trim();
+  if (!url) continue;
+  process.stdout.write(`# ${title || url}\n${url}\n\n`);
+  const child = await import("./content.mjs");
+  const text = await child.fetchAsMarkdown(url);
+  process.stdout.write(text.trimEnd() + "\n\n");
+}

package/skills/browser-use-agent-sdk/SKILL.md

@@ -0,0 +1,90 @@
+---
+name: browser-use-agent-sdk
+description: Minimal agent framework (bu-agent-sdk) for tool-call loops. Use when evaluating browser-use/agent-sdk or building a small tool-based agent without heavy abstractions.
+homepage: https://github.com/browser-use/agent-sdk
+type: guide
+license: MIT
+source:
+  repo: https://github.com/browser-use/agent-sdk
+security:
+  openSource: true
+  audit: required
+metadata: {"nexus":{"emoji":"🧭"}}
+---
+
+# browser-use/agent-sdk
+
+`bu-agent-sdk` is a tiny async agent loop for tool calls. It is not a browser by itself.
+You provide tools (e.g., shell, agent-browser CLI) and let the LLM call them.
+
+## Install (recommended: uv)
+
+```bash
+uv venv
+uv add bu-agent-sdk
+```
+
+Fallback (pip):
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install bu-agent-sdk
+```
+
+## Quick eval harness (Wordle)
+
+This wraps the existing `wordle-nyt-run.sh` script as a tool call so the
+agent-sdk loop is actually exercised.
+
+```bash
+cat > /tmp/bu_wordle_eval.py << 'PY'
+import asyncio
+import os
+from bu_agent_sdk import Agent, tool, TaskComplete
+from bu_agent_sdk.llm import ChatAnthropic
+
+@tool("Run the Wordle benchmark script")
+async def run_wordle(args: str) -> str:
+    import subprocess
+    result = subprocess.run(
+        f"bash /Users/tyler/nexus/home/projects/wordle-nyt-run.sh {args}",
+        shell=True,
+        capture_output=True,
+        text=True,
+    )
+    return (result.stdout + result.stderr).strip()
+
+@tool("Signal completion")
+async def done(message: str) -> str:
+    raise TaskComplete(message)
+
+model = os.environ.get("LLM_MODEL", "haiku")
+agent = Agent(
+    llm=ChatAnthropic(model=model),
+    tools=[run_wordle, done],
+    require_done_tool=True,
+)
+
+async def main():
+    prompt = (
+        "Run Wordle benchmark with: --session bu-agent "
+        "--timing guess-only --wait-ms 300 --key-delay-ms 10 --no-screenshot. "
+        "Then call done with the RESULT line."
+    )
+    result = await agent.query(prompt)
+    print(result)
+
+asyncio.run(main())
+PY
+
+LLM_MODEL=haiku python /tmp/bu_wordle_eval.py
+```
+
+Notes:
+- This is still **no-cheating**. The solver uses a local word list only.
+- Use a unique `--session` per run to avoid Wordle state collisions.
+
+## References
+
+- Repo: https://github.com/browser-use/agent-sdk

package/skills/camsnap/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: camsnap
+description: Capture frames or clips from RTSP/ONVIF cameras.
+homepage: https://camsnap.ai
+metadata: {"nexus":{"emoji":"📸","requires":{"bins":["camsnap"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/camsnap","bins":["camsnap"],"label":"Install camsnap (brew)"}]}}
+---
+
+# camsnap
+
+Use `camsnap` to grab snapshots, clips, or motion events from configured cameras.
+
+Setup
+- Config file: `~/.config/camsnap/config.yaml`
+- Add camera: `camsnap add --name kitchen --host 192.168.0.10 --user user --pass pass`
+
+Common commands
+- Discover: `camsnap discover --info`
+- Snapshot: `camsnap snap kitchen --out shot.jpg`
+- Clip: `camsnap clip kitchen --dur 5s --out clip.mp4`
+- Motion watch: `camsnap watch kitchen --threshold 0.2 --action '...'`
+- Doctor: `camsnap doctor --probe`
+
+Notes
+- Requires `ffmpeg` on PATH.
+- Prefer a short test capture before longer clips.