Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Haroon966/pinky-cursor --skill agent-channelsgit clone --depth 1 https://github.com/Haroon966/pinky-cursorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/haroon966/pinky-cursor/agent-channels)<a href="https://agentmods.dev/skills/haroon966/pinky-cursor/agent-channels"><img src="https://agentmods.dev/badge/skills/haroon966/pinky-cursor/agent-channels/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haroon966/pinky-cursor/agent-channels"><img src="https://agentmods.dev/badge/skills/haroon966/pinky-cursor/agent-channels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00948 |
| Opus 5 | $0.00028 | $0.00474 |
| Sonnet 5 | $0.00011 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
agent-channels scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent channels (WhatsApp / Slack)
When to run
- Right after Pinky install (step 6): WhatsApp · Slack · skip.
- User asks to connect / reconnect later.
Lessons (do not repeat)
| User pain | Fix |
|---|---|
| Agent runs login → no scannable QR in chat | User runs login.sh in their terminal |
MCP + watch.sh same auth → disconnect 440 |
Never run Baileys MCP and watch together |
| “Same message” spam | No fixed auto-ack; agent reply only |
| Laptop chat required | watch.sh + Cursor CLI agent (PC stays on, IDE optional) |
| Owner texts wrong number | Owner texts the linked (QR) account |
| Inbox empty / LID mismatch | Login once; watch saves lid in owner.json |
agent trust / auth fails |
agent login + --trust in watch |
| Secrets on GitHub | .pinky/ gitignored |
Unofficial WhatsApp Web clients can conflict with WhatsApp ToS — prefer a dedicated number for the linked device.
Safety
- Everything under
.pinky/is local (gitignored). Never commit sessions/tokens. - Never print tokens/secrets.
Ask
- Channel: WhatsApp · Slack · skip (multi-select OK).
- If WhatsApp: owner number (who may message the agent). Save
.pinky/whatsapp/owner.json.
WhatsApp — phone controls Cursor (supported path)
Do NOT run login.sh / watch.sh / QR yourself. Print exact commands. Wait for user.
1. Files
Ensure under .pinky/whatsapp/:
login.sh,watch.sh,doctor.sh(fromskills/agent-channels/scripts/)chmod +xthose scripts
2. Owner
Ask phone. Normalize JID (PK 0343… → 92343…@s.whatsapp.net). Write owner.json:
{ "phone": "03435971748", "jid": "[email protected]" }
3. Doctor (give user)
export PATH="$HOME/.local/bin:$PATH"
bash /path/to/project/.pinky/whatsapp/doctor.sh
Fix every FAIL (install agent, agent login, pair, kill MCP whatsapp conflict).
4. Pair (user terminal — QR visible there)
bash /path/to/project/.pinky/whatsapp/login.sh
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/mcp-stdout-guard.cjs 988 B runs code
- scripts/run-mcp.sh 295 B runs code
- scripts/whatsapp-doctor.sh 3.5 KB runs code
- scripts/whatsapp-login.sh 3.1 KB runs code
- scripts/whatsapp-watch.sh 12 KB runs code
- templates/gitignore-fragment 51 B
- templates/mcp-slack.snippet.json 264 B
- templates/mcp-whatsapp.snippet.json 180 B
- templates/owner.example.json 191 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 113 lines · 56 tokens per session scan A 7fcb3783e3f2
agent-channels is a skill published in the GitHub repository Haroon966/pinky-cursor (4 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 948 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…