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 agentmods add skills/open330/context-compress/statsnpx skills add Open330/context-compress --skill statsgit clone --depth 1 https://github.com/Open330/context-compressWhat 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 | $0.00013 | $0.00088 |
| Opus 5 | $0.00006 | $0.00044 |
| Sonnet 5 | $0.00003 | $0.00018 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
context-compress:stats 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 2d 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
Call the mcp__context-compress__stats tool to get session statistics.
CRITICAL: Copy-paste the ENTIRE tool output as markdown. Do NOT summarize or truncate any tables.
After the raw output, add one summary line: "Context-compress has processed X data and kept Y% out of context this session."
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.
- 2d ago First seen · 12 lines · 13 tokens per session scan A 314841912b62
context-compress:stats is a skill published in the GitHub repository Open330/context-compress (2 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 88 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 2026-08-31.
Other skills, from other repositories
scrim
Report what Scrim thinned from tool output and API-equivalent token mix. Use when the user runs /scrim, or asks about quota, context burn, or tool-output size.
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
clean-code
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments.
decision-ledger
Maintain an append-only decision ledger (DECISIONS.md). Use when the user confirms a decision, reverses or changes a past decision, asks what was decided and why, or at session start to load standing decisions.
security-review
Use when reviewing code for vulnerabilities, checking diffs for injection/XSS/auth/crypto issues. Invokes on code changes (.go/.py/.js/.ts/.java/.rs/.php/.rb), not docs-only diffs.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session - dispatches visible YesMem swarm agents per task with two-stage review.