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 replygit 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/reply)<a href="https://agentmods.dev/skills/jigripokri/poha/reply"><img src="https://agentmods.dev/badge/skills/jigripokri/poha/reply.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00423 |
| Opus 5 | $0.00012 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
reply 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 7d 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
/reply
User shows you a thread. You return three plausible replies and a recommendation. They pick.
Recipe
-
Read the thread. Last 10–20 messages.
-
Identify the actual question or ask. Strip pleasantries. What does this message actually want from the user?
-
Read memory/people.md and memory/commitments.md for relevant context (e.g., have they already promised something here?).
-
Draft three options that span the strategy space:
- Option A — Direct yes/agreement: shortest path forward.
- Option B — Push back or qualify: where the user has constraints, hesitation, or a different read.
- Option C — Buy time or redirect: defer, ask a clarifying question, change the venue.
-
Recommend one based on:
- User's stated priorities in life.md
- The relationship's pattern (from people.md)
- Open commitments that might be affected
-
Format the output as:
**They said:** <one-line restatement of the ask>
**Option A — <flavor>**
<draft text>
**Option B — <flavor>**
<draft text>
**Option C — <flavor>**
<draft text>
**Recommendation: <A/B/C>.** <One sentence why.>
**Wildcard:** <one contrarian take they might not have considered>
- Wait for user to pick. "Send A" → invoke /draft to send Option A.
Voice rules
Match the recipient's tone. See /draft for full voice rules.
When NOT to give 3 options
If the message clearly has only one reasonable response (e.g., a simple yes/no logistical question), just give the one reply and a note about why options aren't useful here.
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.
- 7d ago First seen · 57 lines · 24 tokens per session scan A 06c28eeb3449
reply is a skill published in the GitHub repository jigripokri/POHA (118 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 423 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
rich-post
Send a Telegram rich-media post to ANOTHER allowlisted chat via the bot (Bot API 10.1 sendRichMessage) - text, inline images, tables, headings, lists, quotes, collapsible blocks, formulas, collages/slideshows ALL in one message bubble. Use when the owner asks to post somewhere other than the current conversation (the…
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.
memory-processor
Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…
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.
update-recovery
A procedure for recovering custom changes after an Iva software update creates conflicts between the old and new versions.
security-defense
Procedures for handling untrusted content, suspected prompt injection, secret exposure, data exfiltration, and manual security inspection. Use for emails, web pages, forwarded messages, webhooks, group content, or a suspected leak. Do not use as a general claim that every command or model call is automatically…