context-sentinelMonitors session context and automatically manages model switching based on a cascading protocol. Use as part of a heartbeat or cron job to maintain session health and optimize token usage.
Install via ClawdBot CLI:
clawdbot install Nietzsche247/context-sentinelThis skill provides a script to automate the "Cascading Model Protocol," ensuring the agent gracefully degrades from high-cost models to high-context models as the session grows.
This skill operationalizes the logic defined in MEMORY.md.
This skill is designed to be run periodically, either via a cron job or as part of the main agent's HEARTBEAT.md checklist.
Run the check_context.ps1 script to get the current session status and determine the required action.
powershell -File scripts/check_context.ps1The script will return one of three possible string commands:
SWITCH_TO:HANDOFF_NOWSTATUS_OKBased on the output, execute the appropriate agent command.
SWITCH_TO:, run session_status with the new model ID:
session_status model=<model_id>HANDOFF_NOW, trigger the handoff process by writing to the handoff file. This is typically done by running a specific, pre-defined prompt or script.STATUS_OK, no action is needed.HEARTBEAT.mdYou can replace the manual checks in your HEARTBEAT.md with a call to this skill's script.
Old HEARTBEAT.md:
## Cascading Model Protocol (Check Every Heartbeat)
1. **Check Status:** Get current model and context %.
2. **Opus 4.6:** If model is `Opus 4.6` and context > 80% -> Switch to `Opus 4.5`.
...New HEARTBEAT.md using this skill:
## Context Sentinel (Check Every Heartbeat)
1. Run `powershell -File skills/context-sentinel/scripts/check_context.ps1`.
2. Evaluate the output and take action (`SWITCH_TO`, `HANDOFF_NOW`, or `STATUS_OK`).This makes the logic reusable and keeps the HEARTBEAT.md file clean and focused on execution.
Generated Mar 1, 2026
Automates model switching in a customer support chatbot to maintain session health as conversation history grows, ensuring consistent response quality while optimizing token costs. It prevents context overflow by downgrading models or triggering handoffs to human agents when needed.
Manages long sessions for AI agents analyzing legal documents, switching from high-cost to high-context models as more text is processed to balance accuracy and operational expenses. This ensures efficient handling of extensive case files without performance degradation.
Optimizes AI tutoring sessions by monitoring context usage, allowing seamless model transitions to maintain interactive learning as student queries accumulate. It helps reduce costs while providing uninterrupted educational support across lengthy study sessions.
Supports AI-driven patient triage systems by automatically managing model switches based on session length, ensuring reliable symptom assessment while controlling computational resources. This aids in handling extended consultations efficiently.
Enables financial advisors to use AI for extended client meetings, with the skill adjusting models to maintain context awareness and optimize token usage during complex discussions about investments and planning.
Offers the skill as part of a subscription-based AI agent platform, charging monthly fees for automated context management and model optimization features. Revenue is generated from tiered plans based on usage levels and support.
Monetizes the skill by charging based on the number of context checks or model switches performed, appealing to users with variable session needs. Revenue scales with usage, making it cost-effective for sporadic or high-volume applications.
Sells the skill through enterprise licenses for large organizations, including customization, integration support, and premium features for managing multiple AI agents. Revenue comes from one-time purchases or annual contracts with maintenance fees.
đŹ Integration Tip
Integrate the skill by adding the PowerShell script call to your agent's heartbeat or cron job, ensuring output parsing logic is in place to handle switch commands automatically.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Collaborative thinking partner for exploring complex problems through questioning
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
ć šćŽç¨ćˇçĺč˝éćąďźĺŽćä¸ VeADK ç¸ĺ łçĺč˝ă
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.