← Back to Skills Marketplace
adnxone

NXT Pulse Agent

by Adrian Marian Paunescu · GitHub ↗ · v0.5.0 · MIT-0
cross-platform ✓ Security Clean
176
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install nxt-pulse-agent
Description
An adaptive proactive agent skill that manages user energy levels and task prioritization using semantic pulse checks.
Usage Guidance
This skill appears coherent with its stated purpose and does not request credentials or perform network calls. Before installing: (1) Review and restrict the config value CONTEXT_SOURCES to only the specific non-sensitive files you want the agent to read (avoid pointing it at full home directories, system logs, or medical records unless you intend that). (2) Be aware it will create/write memory/pulse-state.json and memory/pulse-history.jsonl in the agent working directory — inspect and rotate or protect those files if they contain sensitive notes. (3) Note the code looks for trigger files (temp_deadline_trigger.txt, memory/critical_deadlines.txt, memory/deadlines/YYYY-MM-DD.txt) that can force a CRITICAL override — ensure other skills or scripts can't create those files unintentionally. (4) If you plan to allow autonomous invocation, monitor initial runs and review logs to confirm behavior matches expectations. If you want higher assurance, review the repository linked in package.json or run the pulse.js in a sandbox first.
Capability Analysis
Type: OpenClaw Skill Name: nxt-pulse-agent Version: 0.5.0 The NXT Pulse Agent is a task management skill designed to adjust agent proactivity based on user energy levels. The code in pulse.js is limited to local file system operations within the application's working directory for state management and logging, with no network access or external dependencies. While the SKILL.md instructions allow the agent to read user-defined context files, this behavior is transparently documented and aligned with the stated purpose of providing context-aware support.
Capability Assessment
Purpose & Capability
Name/description (energy-level monitoring and proactive nudges) match the included code and documentation. pulse.js implements cooldowns, state/history logging, and deadline triggers using local files under the working directory (memory/...). No unexpected services, credentials, or external binaries are required.
Instruction Scope
SKILL.md instructs the agent to read configured CONTEXT_SOURCES (relative paths) and to use openclaw.json for configuration. That matches pulse.js behavior. This is in-scope, but the skill will read whatever files you list in CONTEXT_SOURCES (examples in docs include journals and medical logs) — those can be highly sensitive so the user should limit configured paths carefully.
Install Mechanism
There is no install spec and no network downloads. The skill is instruction-first but includes a small, readable pulse.js. No external installers, URL downloads, or extracted archives were present — low install risk.
Credentials
The skill declares no required environment variables or credentials. The code only accesses local filesystem paths (state/history, deadline trigger files). No secrets, API keys, or unrelated credentials are requested.
Persistence & Privilege
The skill writes its own state and audit history to memory/pulse-state.json and memory/pulse-history.jsonl in the agent's working directory — this is expected. always:false and default autonomous invocation are used (normal). If you enable autonomous runs, consider that the skill can create/read those memory files and trigger proactivity according to its logic.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install nxt-pulse-agent
  3. After installation, invoke the skill by name or use /nxt-pulse-agent
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.5.0
v0.5.0: Generic adaptive pulse, /pulse command, and token guardrails.
v0.3.1
Documentation update: highlighted semantic energy detection and corrected versioning.
v0.3.0
Switched from keyword-based detection to LLM-driven semantic urgency detection. The agent now uses reasoning to identify deadlines and triggers the pulse via local state files.
v0.2.2
Made deadline detection language-independent by adding multi-language urgency markers (RO, EN, ES, FR).
v0.2.1
Mitigated security audit concerns: improved implementation transparency and added date-matching logic for deadlines in MEMORY.md
v0.2.0
nxt-pulse-agent v0.2.0 - Introduces proactive energy-aware task management, with "Pulse Checks" tailored for ADHD and fluctuating energy levels. - Adds "Just 2 Minutes" micro-step mode for low energy states, preventing overwhelm and supporting inertia-breaking action. - Implements Critical Override: deadlines within 6 hours bypass snooze to avoid missed priorities. - All agent nudges, overrides, and rationales are transparently logged for review. - Visual pulse system (🟢/🟡/🔴) provides immediate feedback on energy status and task recommendations. - Enhances integration with logs, memory, and calendar/task data for smarter, context-driven support.
Metadata
Slug nxt-pulse-agent
Version 0.5.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 6
Frequently Asked Questions

What is NXT Pulse Agent?

An adaptive proactive agent skill that manages user energy levels and task prioritization using semantic pulse checks. It is an AI Agent Skill for Claude Code / OpenClaw, with 176 downloads so far.

How do I install NXT Pulse Agent?

Run "/install nxt-pulse-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is NXT Pulse Agent free?

Yes, NXT Pulse Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does NXT Pulse Agent support?

NXT Pulse Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created NXT Pulse Agent?

It is built and maintained by Adrian Marian Paunescu (@adnxone); the current version is v0.5.0.

💬 Comments