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 IgorWarzocha/howaboua-pi-stuff --skill pulsesgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/pulses)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/pulses"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/pulses/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/igorwarzocha/howaboua-pi-stuff/pulses"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/pulses.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 | $0.00014 | $0.00399 |
| Opus 5.5 | $0.00006 | $0.00160 |
| Sonnet 5.5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
pulses 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 9d 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
Create .pi/pulses/<self-explanatory-name>.md with a lowercase kebab-case filename. In Git, use the original repository root, not a linked worktree. Otherwise use the main session's working directory.
---
schedule: every 5h
enabled: true
quietHours: 22:00-08:00
---
Check the agreed sources for changes since the previous run.
Post actionable findings to the designated available destination.
schedule is required: manual, every 30m, every 5h, every 2d, daily 09:00, weekly fri 17:00 or at <datetime>. Use an explicit timezone offset for a one-time timestamp when timezone matters. Daily and weekly times and quietHours use the host's local timezone. Checks run every five minutes.
enabled defaults to true. Set it to false to pause automatic runs while keeping explicit runs available. quietHours is optional and accepts HH:MM-HH:MM, including overnight ranges. Optional title replaces the filename as the display title.
Keep the body a short SOP: the actual task, sources, destination and consequential limits. Do not duplicate general skill guidance or require loading skills that the task does not need. Define concrete destinations only when available. The worker receives the body plus standard result-routing and procedural-feedback instructions, so do not repeat those instructions in each definition.
Use ordinary file tools to edit definitions. Disable routines worth keeping for later; delete obsolete ones. There is no separate configuration API. pulses({}) lists paths and flags invalid definitions. pulses({run: "name"}) requests an immediate run, including when automatic scheduling is disabled. Explicit runs bypass quiet hours and leave the recurrence schedule unchanged.
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.
- 9d ago Changed · +4 lines b161fba3c6c3
- 18d ago First seen · 24 lines · 14 tokens per session scan A e0272e8b92be
pulses is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (413 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 399 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 2026-10-19.
pulses compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pulsesIgorWarzocha/howaboua-pi-stuff | Skill | 413 | yesterday | MIT | A | 14 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | today | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |