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 coyvalyss1/model-matchmaker --skill context-monitorgit clone --depth 1 https://github.com/coyvalyss1/model-matchmakerWrote 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/coyvalyss1/model-matchmaker/context-monitor)<a href="https://agentmods.dev/skills/coyvalyss1/model-matchmaker/context-monitor"><img src="https://agentmods.dev/badge/skills/coyvalyss1/model-matchmaker/context-monitor/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/coyvalyss1/model-matchmaker/context-monitor"><img src="https://agentmods.dev/badge/skills/coyvalyss1/model-matchmaker/context-monitor.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 | $0.00043 | $0.01857 |
| Opus 5 | $0.00022 | $0.00928 |
| Sonnet 5 | $0.00009 | $0.00371 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
context-monitor 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAX Mode Prevention & Context Monitoring
The Problem
Cursor's MAX mode (Claude Opus 3.5, 200K token context) is expensive and should be reserved for truly complex tasks. Context can balloon quickly when:
- Opening large files (e.g., a 9,378-line React component)
- Loading chat transcripts or logs (1-10MB)
- Accumulating tool calls and responses across long sessions
- Reading multiple files speculatively
Once context exceeds 200K tokens, the conversation is forced into a new chat with a handoff summary. This wastes user time and disrupts flow.
The Solution
Monitor context throughout the conversation (not just at start). Warn at thresholds and proactively recommend starting a new chat with a clean handoff.
Token Thresholds
🟡 Yellow Alert (100K tokens)
Action: Note the context size internally. No user warning yet.
🟠 Orange Alert (150K tokens)
Action: Warn the user and suggest wrapping up current work or starting a new chat if the task is open-ended.
Warning format:
⚠️ Context approaching 150K tokens. Consider starting a new chat after this task to avoid MAX mode. I can generate a handoff summary.
🔴 Red Alert (180K tokens)
Action: Strongly recommend starting a new chat. Offer to generate a handoff summary immediately.
Warning format:
🚨 Context at 180K tokens (MAX mode limit: 200K). Recommend starting a new chat now. I can generate a handoff summary with:
- Task description
- Progress so far
- Next steps
- @file references
Automatic Triggers
Issue a warning automatically when:
-
Large file opened (>3,000 lines):
- Example: DashboardPage.jsx (9,378 lines) = ~70K tokens
- Example: useChatManager.jsx (4,178 lines) = ~30K tokens
- Any file >5,000 lines = likely >40K tokens
-
Multiple large files in context (>5 files over 1,000 lines each)
-
Long conversation (>50 tool calls in current chat)
-
Transcript search (reading agent-transcripts/*.txt files)
-
Plan file creation (plans are meta-work that inflate context)
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 · 227 lines · 43 tokens per session scan A 88ad76fe2def
context-monitor is a skill published in the GitHub repository coyvalyss1/model-matchmaker (168 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,857 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.