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 djangonavarro220/agentic-life-os --skill routines-heartbeatgit clone --depth 1 https://github.com/djangonavarro220/agentic-life-osWrote 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/djangonavarro220/agentic-life-os/routines-heartbeat)<a href="https://agentmods.dev/skills/djangonavarro220/agentic-life-os/routines-heartbeat"><img src="https://agentmods.dev/badge/skills/djangonavarro220/agentic-life-os/routines-heartbeat/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/djangonavarro220/agentic-life-os/routines-heartbeat"><img src="https://agentmods.dev/badge/skills/djangonavarro220/agentic-life-os/routines-heartbeat.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 | $0.00017 | $0.01021 |
| Opus 5 | $0.00009 | $0.00511 |
| Sonnet 5 | $0.00003 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
routines-heartbeat 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 12d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
routines-heartbeat
Mandatory integrity contract
Before acting, load and follow ../../references/data-integrity.md. Its provenance, missing-value, correction-history, defensive-write, backup, and recovery rules are mandatory for this subskill.
Run a quiet, frequent check for actionable changes. This routine exists to prevent dropped commitments and stale state, not to send “I checked and nothing happened” spam.
This is a dynamic heartbeat, not a fixed checklist. It should discover the runtime's current capability inventory, choose relevant active watch targets, perform dynamic skill loading for the adapters needed in this run, and stay silent unless something actionable changed.
Trigger
Use for:
- scheduled frequent checks
- “watch this quietly” requests
- follow-up monitoring where silence is acceptable
- detecting changed state since the last run
Do not use for deep weekly review, full daily briefing, or open-ended life planning. Those belong to routines-pulse, routines-weekly-review, or context-now.
Inputs to inspect
Load only sources configured in the relevant skill data files under $LIFEOS_DATA_DIR/<skill-name>/data.json and the global runtime_inventory in $LIFEOS_DATA_DIR/config.json. Runtime-owned sources may include:
- runtime TODO/task system
- runtime cron/job state
- recent Life OS private state
- active watch targets approved by the user or runtime policy
- user-provided watch targets
- mail/calendar only if explicitly configured by the runtime/user
Do not scrape every possible source. Cheap and relevant beats exhaustive and noisy. Also do not hard-code a universal list of checks: the heartbeat should look at configured watch targets and the capability inventory, then select the smallest useful set for this run.
Capability inventory and dynamic loading
The capability inventory records what the active runtime can do and how to reach it:
- skill sources and skill names, for example mail, calendar, tasks, cron, memory, health, finance, or travel adapters;
- tool sources, if the runtime exposes tools separately from skills;
- source pointers and access notes;
- active watch targets with cadence, alert condition, no-news policy, and last-observed pointer;
- missing capabilities that should be proposed to the user instead of guessed.
What ships with it
1 file 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.
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.
- 12d ago First seen · 118 lines · 17 tokens per session scan A 662084620eba
routines-heartbeat is a skill published in the GitHub repository djangonavarro220/agentic-life-os (11 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,021 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.