Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add NodeNestor/claude-rolling-context/plugin install rolling-contextWrote 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/nodenestor/claude-rolling-context/restart)<a href="https://agentmods.dev/commands/nodenestor/claude-rolling-context/restart"><img src="https://agentmods.dev/badge/commands/nodenestor/claude-rolling-context/restart.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00205 |
| Opus 5 | $0.00014 | $0.00102 |
| Sonnet 5 | $0.00005 | $0.00041 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade B, and why
restart scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
export ROLLING_CONTEXT_FORCE_RESTART=1; (powershell -ExecutionPolicy Bypass -File "${CLAUDE_PLUGIN_ROOT}/hooks/start-proxy.ps1" 2>/dev/null || bash "${CLAUDE_PLUGIN_ROOT}/hooks/start-proxy.sh" 2>/dev/null); tail -n 6 "$H What it actually says
Run this command and show the user the log lines it prints, verbatim. Add no commentary beyond one short line if something looks wrong.
The start hook never downgrades a running proxy and never replaces one that has requests in flight from other sessions — it defers such upgrades. This forces the restart: it still waits up to ~6 seconds for in-flight requests to finish, then replaces whatever is serving with this plugin's version.
export ROLLING_CONTEXT_FORCE_RESTART=1; (powershell -ExecutionPolicy Bypass -File "${CLAUDE_PLUGIN_ROOT}/hooks/start-proxy.ps1" 2>/dev/null || bash "${CLAUDE_PLUGIN_ROOT}/hooks/start-proxy.sh" 2>/dev/null); tail -n 6 "$HOME/.claude/rolling-context-hook.log"
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.
- 4d ago First seen · 16 lines · 27 tokens per session scan B 964e62ba266a
restart is a command published in the GitHub repository NodeNestor/claude-rolling-context (31 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 205 once invoked, about $0.0001 per session on Opus 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 2026-09-04.
Other commands, from other repositories
ops-grafana-dashboard
Creation of Grafana dashboards with automatic provisioning.
ops-vercel
Command "ops-vercel" from christopherlouet/claude-base, covering ops-vercel agent (pointer), context, delegate to the vendor toolkit and related agents.
ops-monitoring
Code instrumentation for monitoring/logging/alerting and deploying the observability stack.
ops-infra-code
Implements Infrastructure as Code (IaC) with Terraform, CloudFormation or Pulumi.
ops-serverless
Deployment of serverless applications (AWS Lambda, Vercel, Cloudflare Workers).
ops-vps
Deployment to a VPS server (OVH, Hetzner, DigitalOcean, Scaleway, etc.).