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 tao12345666333/ankaloop --skill heartbeatgit clone --depth 1 https://github.com/tao12345666333/ankaloopWrote 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/tao12345666333/ankaloop/heartbeat)<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/heartbeat"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/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/tao12345666333/ankaloop/heartbeat"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/heartbeat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00506 |
| Opus 5.5 | $0.00017 | $0.00202 |
| Sonnet 5.5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
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 yesterday.
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
Heartbeat
Periodic agent wake-up to check for tasks in HEARTBEAT.md.
How It Works
- Every 30 minutes, the scheduler triggers this skill
- Read
HEARTBEAT.mdfrom the workspace root - If file is empty or has no actionable content → reply
[SILENT]and stop - If file has tasks → execute them one by one
- Mark completed tasks by moving them to the
## Completedsection - If
telegram-senderskill is available and the task warrants notification, send a Telegram update
HEARTBEAT.md Format
# Heartbeat Tasks
## Active Tasks
- Check CI status for open PRs and fix any failures
- Review and merge dependabot PRs if tests pass
## Completed
- [2026-02-17] Cleaned up stale branches
Rules
- Empty = skip: If
HEARTBEAT.mdis missing, empty, or only has headers/comments, reply[SILENT] - Task markers: Lines starting with
-under## Active Tasksare actionable - Completion: After finishing a task, move it to
## Completedwith today's date prefix - Errors: If a task fails, leave it in Active Tasks and append
(FAILED: reason)to the line - Safety: Never delete
HEARTBEAT.md, only modify task entries - Scope: Tasks should be self-contained and completable within the timeout (5 minutes)
Skipable Content
These are not actionable (skip them):
- Empty lines
- Lines starting with
#(headers) - Lines starting with
<!--(HTML comments) - Lines with only
- [ ]or- [x](empty checkboxes)
What ships with it
2 files 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.
- yesterday Changed c3fcacf5e4e7
- 1mo ago First seen · 55 lines · 42 tokens per session scan A ec00b4f289f2
heartbeat is a skill published in the GitHub repository tao12345666333/ankaloop (55 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 506 once invoked, about $0.0002 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
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
ask-dora
Use when the teammate types /ask-dora, or asks any Dora question, a routine idea, a pocket job, dora harness new, or a connector catalog question.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
grilling
A guided questioning process for testing a plan, decision, or idea. It maps dependent choices into a tree and asks only the questions that can be answered at each stage.
learn
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.