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 gsdgit 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/gsd)<a href="https://agentmods.dev/skills/jigripokri/poha/gsd"><img src="https://agentmods.dev/badge/skills/jigripokri/poha/gsd/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/gsd"><img src="https://agentmods.dev/badge/skills/jigripokri/poha/gsd.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 | $0.00022 | $0.00494 |
| Opus 5.5 | $0.00009 | $0.00198 |
| Sonnet 5.5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
gsd 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 2mo 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
/gsd
User says "/gsd" or "what should I do next?" You return a prioritized punch list.
Recipe
-
Read memory/commitments.md. Filter to PENDING + OVERDUE.
-
Read Google Tasks (via Chrome → tasks.google.com). All open items from primary lists.
-
Read memory/life.md > This Month / This Week. Anything that should be active.
-
Prioritize using the GSD ranking:
- P0 — Overdue + blocking someone else: do today, in the next 2 hours if possible
- P1 — Overdue, self-blocked: do today
- P2 — Today's commitments: scheduled for today, not done
- P3 — This week: due in next 5 days
- P4 — Quick wins: < 10 min items, batch them
- P5 — Aging but not urgent: > 7 days old, no due date — flag for review/punt
-
Format the output as:
🎯 GSD — <current time>
P0 (do now):
1. <title> — <est time> — <one-line why it matters>
2. ...
P1 (do today):
1. <title> — <est time>
...
P2 (today's scheduled):
...
Quick wins (5 min, batch these):
- <item>
- <item>
To punt or kill: <N> items aging past usefulness — review during weekly?
**Wildcard:** <one observation about the list — pattern, hidden priority, missing item>
- Suggest a focus block. "If you only have 90 min today, do P0 + the top 2 of P1."
What this skill is for
When the user feels overwhelmed and wants to be told what to do. Returns a clear ranked list, not a vague "you have a lot going on."
What this skill is NOT
- A todo list manager. The exocortex doesn't modify Google Tasks unless asked.
- A motivator. No "you got this!" — direct ranking, that's it.
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.
- 2mo ago First seen · 62 lines · 22 tokens per session scan A c994fdf48ddd
gsd is a skill published in the GitHub repository jigripokri/POHA (121 stars, last pushed 6d ago), licensed MIT. It adds 22 tokens to every session and 494 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
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.
insight
A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.
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.
brief
Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn, on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.
scheduling
A scheduling tool for creating reminders and recurring tasks, or running commands at set times. It can list, move, cancel, and immediately run scheduled items.
welcome
Introduce yourself to a newly connected channel. Triggered automatically when a channel is first wired. Send a friendly greeting and brief overview of what you can do.