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 jigripokri/POHA --skill draftgit clone --depth 1 https://github.com/jigripokri/POHAWrote 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/jigripokri/poha/draft)<a href="https://agentmods.dev/skills/jigripokri/poha/draft"><img src="https://agentmods.dev/badge/skills/jigripokri/poha/draft/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/jigripokri/poha/draft"><img src="https://agentmods.dev/badge/skills/jigripokri/poha/draft.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 | $0.00035 | $0.00519 |
| Opus 5.5 | $0.00014 | $0.00208 |
| Sonnet 5.5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
draft 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 1mo 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.
What it actually says
/draft
Write outbound messages in the user's voice. Used on demand for any thread.
Recipe
When invoked:
-
Identify the thread. User says "draft a reply to " or "draft a message to about ." If ambiguous, ask one clarifying question.
-
Read the last 10–20 messages in the thread. Use the appropriate MCP (WhatsApp, Gmail, Android Messages).
-
Study voice patterns.
- Sentence length and structure
- Vocabulary level (formal vs. casual)
- Regional slang or in-group references
- Punctuation habits
- Use of emoji or not
- Greeting/sign-off patterns (or lack thereof)
-
Read CLAUDE.md > Voice & Drafting Authorization.
-
Read memory/people.md for context on the recipient (if available).
-
NEVER read memory/private/carry-on.md. Do not reference anything from it.
-
Draft 1–3 options. If user said "draft" (singular), give one. If user said "options" or the message is high-stakes, give 2–3 with brief notes on the difference.
-
Show the draft(s). Do NOT send.
-
Wait for approval. "Send it", "send A", "send the second one" = green light. Anything else means iterate.
-
On approval, send via the appropriate MCP.
Voice rules (default — override in CLAUDE.md)
- Direct. No "Hope this finds you well."
- Match the recipient's tone — if they're casual, you're casual.
- Reference something specific from the recent conversation (callback, shared joke, thing they mentioned).
- Short. Two paragraphs maximum unless the topic genuinely requires more.
- No AI tells: "As an AI...", "I hope this helps...", "Let me know if you have any questions!" — never.
What this skill won't do
- Send before "send it" approval. Always wait.
- Quote anything from carry-on.md.
- Send to multiple recipients without confirming the list explicitly.
- Send if the draft contradicts something obvious from memory (e.g., agreeing to a date the user has a conflict on).
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.
- 1mo ago First seen · 54 lines · 35 tokens per session scan A fc0f5520e9fb
draft is a skill published in the GitHub repository jigripokri/POHA (121 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 519 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
rich-replies
Shape a reply for Telegram: headings, tables, folds, footnotes, formulas, pictures, slideshows, maps, and buttons (choice, link, copy, mini app) inside the text. Load before a structured answer, a comparison, a report in chat, or whenever you offer the user a choice or a link.
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
rich-post
Send a rich Telegram post to ANOTHER allowlisted chat; not for the current chat reply or plain reports.
update-recovery
Use when an update leaves out owner customizations or they need restoring or merging.
agent-browser
A command-line browser for interactive websites and web apps. It can open pages, inspect clickable elements, fill forms, click buttons, take screenshots, sign in, and read pages whose content is loaded by JavaScript.
watch
A monitoring and briefing workflow that checks unread Telegram messages, email, failed checks, and failed scheduled units, then decides what needs the owner's attention. It can also explain actions such as creating a task, delaying a reminder, ignoring an item, or fixing a failure.