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 agents/vkirill/claude-lane-stack/memory-maintainergit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/agents/vkirill/claude-lane-stack/memory-maintainer)<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/memory-maintainer"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/memory-maintainer.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 | $0.00032 | $0.00165 |
| Opus 5 | $0.00016 | $0.00082 |
| Sonnet 5 | $0.00006 | $0.00033 |
| Haiku 4.5 | $0.00003 | $0.00016 |
Grade A, and why
memory-maintainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
memory-maintainer
Shell-out. Provider/model come from adoc stages.memory.
export PATH="$HOME/.agents/bin:$PATH"
memory-maintain-project "$PROJECT_CWD" "${SINCE:-24 hours ago}"
If stages.memory.enabled is false, the script exits 0 with SKIP. Do not
invent a corpus. Last line: DONE <report> or FAILED <reason>.
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 · 23 lines · 32 tokens per session scan A 369c666e0e66
memory-maintainer is an agent published in the GitHub repository VKirill/claude-lane-stack (114 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 165 once invoked, about $0.0002 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 agents, from other repositories
performance-engineer
Analyzes hot paths, N+1 queries, unbounded operations, memory leaks, and scaling behavior. Reports only findings with confidence >= 80.
rag-specialist
Expert consultant for retrieval-augmented generation, knowledge bases, intelligent document processing, and semantic search systems. Use proactively for RAG architecture analysis, knowledge system design, document processing strategies, and semantic search optimization. Provides consultation and recommendations only …
unsloth-specialist
Expert consultant for Unsloth fine-tuning framework, memory optimization, training acceleration, and efficient model customization. Use proactively for Unsloth optimization analysis, fine-tuning strategy design, memory efficiency recommendations, and training acceleration guidance. Provides consultation and…
game-performance-specialist
Expert consultant for game performance optimization across all platforms and technologies, providing analysis and recommendations without writing code. Use proactively for performance bottleneck analysis, frame rate optimization guidance, memory management strategies, and cross-platform performance consulting. When…
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
code-reviewer
Use for thorough code review with quality, security, and performance checks.