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/on)<a href="https://agentmods.dev/commands/nodenestor/claude-rolling-context/on"><img src="https://agentmods.dev/badge/commands/nodenestor/claude-rolling-context/on.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 | $0.00023 | $0.00155 |
| Opus 5 | $0.00012 | $0.00077 |
| Sonnet 5 | $0.00005 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
on 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 6d 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.
What it actually says
Run this command and show the user its output verbatim, EXCEPT the
<<rolling-context:...>> marker line, which is machinery — do not repeat it
back, quote it, or explain it. Add no commentary beyond one short line if
something looks wrong.
With no arguments this turns compression back on for the current conversation
only. If the user asked to turn it back on everywhere rather than just here,
append --global.
Arguments given by the user: $ARGUMENTS
python "${CLAUDE_PLUGIN_ROOT}/proxy/switch.py" on $ARGUMENTS
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.
- 6d ago First seen · 19 lines · 23 tokens per session scan A f79122c75363
on is a command published in the GitHub repository NodeNestor/claude-rolling-context (31 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 155 once invoked, about $0.0001 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 commands, from other repositories
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
context-stats
Display context window usage and token statistics.
memory-consent
Grant or revoke consent for session-end auto-memorize. Usage: /memory-consent yes|no|ask.
handoff
Create a handoff document for seamless session continuity.
learn
Learn Claude Code best practices and capture lessons into persistent memory.