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/magnifico4625/locus/compactnpx skills add Magnifico4625/locus --skill compactgit clone --depth 1 https://github.com/Magnifico4625/locusWrote 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/magnifico4625/locus/compact)<a href="https://agentmods.dev/skills/magnifico4625/locus/compact"><img src="https://agentmods.dev/badge/skills/magnifico4625/locus/compact.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 | $0.00018 | $0.00143 |
| Opus 5 | $0.00009 | $0.00072 |
| Sonnet 5 | $0.00004 | $0.00029 |
| Haiku 4.5 | $0.00002 | $0.00014 |
Grade A, and why
compact 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 5d 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
Clean up old episodic memory by invoking the memory_compact MCP tool.
By default, removes episodic entries older than 30 days while keeping the 5 most recent sessions intact. Semantic memories (decisions) are never deleted.
What to do
- Call the
memory_compacttool (optionally withmaxAgeDaysandkeepSessionsparameters) - Present the results: how many entries were deleted, how many remain, how many sessions remain
- If nothing was deleted, inform the user that episodic memory is already clean
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.
- 5d ago First seen · 14 lines · 18 tokens per session scan A 688477a5a908
compact is a skill published in the GitHub repository Magnifico4625/locus (14 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 143 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 skills, from other repositories
memory-audit
记忆审计入口。当我主动决定审视记忆质量时，先读此文件判断应使用哪个子技能。.
memory-audit-belief-duel
信念对决。当父子节点内容冲突、或两条你都认可的记忆逻辑上不能并存时使用。.
memory-audit-discoverability
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。.
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.
memory-audit-node-decomposition
节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。.
memory-audit-dead-data-purge
死数据清洗。当一条记忆读不读你的行为都不会变、感悟没有现实锚点时使用。.