memoria-heartbeat

memoria-heartbeat is a skill for Claude Code, Codex from Szotasz/marveen. It costs 44 tokens per session (2,244 once invoked), scanned A, original, MIT.

A skill that records what happened between agent runs and can create new skills from complex work. A heartbeat is a recurring check that keeps this information up to date.

In plain words
What is it for?
Use it to check for pending messages, review recent work, save useful memory, and generate skills when a task reveals reusable methods.
Why use it?
It helps prevent important context from being lost and avoids repeating work that was already recorded in an earlier run.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to check for pending messages, review recent work, save useful memory, and generate skills when a task reveals reusable methods.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/szotasz/marveen/memoria-heartbeat
Install

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.

Any agent
npx skills add Szotasz/marveen --skill memoria-heartbeat
Clone the repo
git clone --depth 1 https://github.com/Szotasz/marveen

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for memoria-heartbeat

README.md
[![agentmods](https://agentmods.dev/badge/skills/szotasz/marveen/memoria-heartbeat/github.svg)](https://agentmods.dev/skills/szotasz/marveen/memoria-heartbeat)
Your own site
<a href="https://agentmods.dev/skills/szotasz/marveen/memoria-heartbeat"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/memoria-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.

agentmods 80×15 button for memoria-heartbeat

Your own site · 80×15
<a href="https://agentmods.dev/skills/szotasz/marveen/memoria-heartbeat"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/memoria-heartbeat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 65
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Data Exfiltration · line 35
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Agent Snooping · line 64
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Rogue Agent · line 64
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.02244
Opus 5 $0.00022 $0.01122
Sonnet 5 $0.00009 $0.00449
Haiku 4.5 $0.00004 $0.00224

Measured 8d ago against content hash bd4690810148, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

memoria-heartbeat scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://localhost:3420/api/memories \
scheduled-tasks/memoria-heartbeat/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

0. ELŐSZÖR: Van-e várakozó Telegram üzenet?

Mielőtt bármit csinálnál, nézd meg a session inputját: ha van <channel source= kezdetű blokk a kontextusban (azaz a felhasználó küldött valamit egy csatornán -- Telegram, Slack, stb.), azonnal válaszolj rá -- a heartbeat logika (A/B/C, csendben maradás) NEM vonatkozik a közvetlen felhasználói üzenetekre. Válasz után folytasd a heartbeat-et.


Nézd át, mi történt az előző memória-kör óta. Két dolgot csinálj:

AZ ABLAK "AZ ELŐZŐ KÖR ÓTA", NEM FIX PERCSZÁM -- MÉRVE 2026-08-22, ÚJRAMÉRVE 2026-08-27. A szöveg korábban fix percszámot mondott, és a rögzített szám KÉTSZER is elavult. Ezért nincs benne szám többé: a fix percszám a konfigurált kadenciával együtt avul, "az előző kör óta" nem.

AMIT 2026-08-27-EN MEGMERTEM, ha valaki mégis a számra kíváncsi (és ne erre építs): a task-config.json */15 * * * *-ot mond, de a skipIfBusy: true miatt a hozzám ELJUTÓ kadencia 30 perc. A task_runs tökéletesen váltakozik: :00 skipped, :15 fired, :30 skipped, :45 fired -- 24 órában 43 fired / 53 skipped, és 17 egymást követő fired-köz pontosan 1800-1803 mp. A :00 és :30 slot rendszeresen ütközik az órás heartbeat-digesttel és a drain-körökkel. Vagyis a KONFIGURÁLT (15) és a KÉZBESÍTETT (30) kadencia két külön szám, és a 2026-08-22-i "a kadencia 15 perc" javítás a konfiguráltat mérte, nem azt, ami ideér. Következmény, amit érdemes tudni: ez a kör soha nem fut :00-kor és :30-kor, tehát az óra tetején történtek a következő (:15 vagy :45) körben jönnek fel. Ez nem hiba, csak fáziseltolás. HA MÉGIS ÁTFEDÉST LÁTSZ: a mérce nem az idő, hanem hogy lezártad-e már. Ha egy munkára már írtál memóriát vagy patcheltél skillt az előző körben, az KÉSZ -- ne írd meg újra más szavakkal.

1. Memória mentés

Ha volt fontos döntés, preferencia, tanulság vagy bármi ami később hasznos, mentsd el:

curl -s -X POST http://localhost:3420/api/memories \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(cat {{INSTALL_DIR}}/store/.dashboard-token)" \
  -d '{"agent_id":"SAJAT_NEVED","content":"...","category":"warm","keywords":"..."}'

Read the full file on GitHub · 120 lines

Files

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.

Changes

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.

  1. 8d ago Changed · +7 lines bd4690810148
  2. 12d ago First seen · 113 lines · 44 tokens per session scan A 35f0d15d320a

Subscribe to this mod's changes

memoria-heartbeat is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 2,244 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories