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.
git clone --depth 1 https://github.com/ArieGoldkin/claude-forgeWrote 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/commands/ariegoldkin/claude-forge/setup-context-monitor)<a href="https://agentmods.dev/commands/ariegoldkin/claude-forge/setup-context-monitor"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/setup-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/commands/ariegoldkin/claude-forge/setup-context-monitor"><img src="https://agentmods.dev/badge/commands/ariegoldkin/claude-forge/setup-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 | $0.00021 | $0.02256 |
| Opus 5.5 | $0.00008 | $0.00902 |
| Sonnet 5.5 | $0.00004 | $0.00451 |
| Haiku 4.5 | $0.00002 | $0.00226 |
Grade B, and why
setup-context-monitor scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
script=$(find "$HOME/.claude/plugins/cache" \ How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup-context-monitor - Configure Context Window Monitoring
One-time setup to enable proactive context window usage warnings. Creates a stable launcher script and configures global settings so context monitoring works across all projects and survives plugin updates.
When to Use
- First time enabling context monitoring
- After reinstalling the plugin (launcher script should still work)
- When context warnings aren't appearing
- To verify the monitoring pipeline is working
Prerequisites
- Continuity toolkit plugin installed and hooks compiled (
cd hooks && npm run build) - Claude Code v2.1.97+ (StatusLine
refreshIntervalandworkspace.git_worktree)
What This Command Does
- Create stable launcher - Write
~/.config/claude/continuity-statusline.shthat finds the plugin script via glob - Configure global StatusLine - Add
statusLine.commandto~/.claude/settings.json(applies to ALL projects) - Verify hook - Confirm context-monitor hook is registered in
hooks.json - Test pipeline - Verify temp file appears after a message exchange
Execution Steps
Step 1: Create the Stable Launcher Script
Create the directory and launcher script at ~/.config/claude/continuity-statusline.sh:
mkdir -p ~/.config/claude
Step 0: Check for an Existing StatusLine
Run this before writing anything:
python3 -c "import json,os;d=json.load(open(os.path.expanduser('~/.claude/settings.json')));print(json.dumps(d.get('statusLine','(unset)')))"
| Existing value | Action |
|---|---|
Unset, or already continuity-statusline.sh |
Proceed |
| Any other program | Stop and ask. Name what is configured and offer Step 1a (compose) or replacement |
Always overwrite the launcher file once the user has chosen ctk (do not skip if it already exists). A pre-existing launcher from an older install may hardcode the legacy continuity-toolkit cache path only and silently fail to [?] unknown once the plugin is renamed or its old cache is cleaned. Re-running this command must self-heal those installs. This is about the launcher script's contents — it is not licence to repoint a statusLine the user deliberately set, which is what Step 0 guards.
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.
- 1mo ago First seen · 205 lines · 21 tokens per session scan B 6d0af75eed56
setup-context-monitor is a command published in the GitHub repository ArieGoldkin/claude-forge (7 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 2,256 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
learn
A command for recording lessons learned from direct notes, recent errors, or the current work session. It can classify lessons, suggest automations from git history, and manage the saved list.
handoff
Write a session handoff document for continuity.
revise-claude-md
Update CLAUDE.md with learnings from this session.
session-save
Save the current session state — decisions, modified files, current status, and next steps — to a handoff file for later resume.
context-audit.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.