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 skills add VKirill/claude-lane-stack --skill lane-memorygit 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/skills/vkirill/claude-lane-stack/lane-memory)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/lane-memory"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/lane-memory.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00059 | $0.00704 |
| Opus 5 | $0.00030 | $0.00352 |
| Sonnet 5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
lane-memory 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lane memory
File corpus for facts that cannot be derived from git or MODULE_MAP. Laws from the SMA 5.6.1 drawing. Off until adoc turns it on.
Info (print and stop)
If $ARGUMENTS is info, or the user says info / справка this skill:
print the block below verbatim (Russian), then stop.
lane-memory — факты проекта, которые нельзя вывести из кода
Зачем
- Правила «всегда так» сидят в ядре и грузятся каждую сессию (не поиск).
- Остальное — по запросу: lane-memory context / search.
- Пишет только команда lane-memory write (одна дверь). Ночной агент не чинит сам.
adoc уже пишет эти крутилки. Включить — Enabled (или enabled: true).
stages:
memory:
enabled: false
maintain: true
inject: true
provider: codex
model: gpt-5.6-terra
reasoning_effort: high
audience: subagent
personal_bot: ""
search_engine: auto
core_budget: 3072
note_budget: 8000
index_budget: 65536
context_budget: 2500
Раскладка
.agents/memory/ корпус в git (был .claude/memory)
.cls/local-memory/ только эта машина, не git (был .sma/local-memory)
.cls/index/ SQLite FTS, производный (был .sma/index)
Потом: lane-memory init .
Черновик-шаблон (любой проект): drafts/_TEMPLATE.md
или skill references/draft-template.md
Фон: memory-maintain-project . "24 hours ago"
Спросить корпус
lane-memory context . "почему сводку не по шаблону"
lane-memory search . "handoff"
lane-memory core .
lane-memory explain . --task "подготовь поставку"
Записать факт (черновик → дверь)
lane-memory write --apply .agents/memory/drafts/<id>.md --confirm .agents/memory/<id>.md --yes
Не класть сюда
структуру репо, git-историю, PROGRESS, YAML рана — у них свои файлы.
Work
If lane-memory enabled . exits 1: do not invent a corpus. Tell the owner
to set stages.memory.enabled: true.
If enabled: on cold start, CORE is already in resume-project. For a task,
run lane-memory context . "<task>" and Read named files. Recalled claim
about the tree is a prompt to lane-memory verify . <id>, not proof.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 76 lines · 59 tokens per session scan A 7e586fbe3587
lane-memory is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 704 once invoked, about $0.0003 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
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
iterative-retrieval
A method for finding the right code context for sub-agents through repeated search, evaluation, and refinement. It addresses the problem that an agent may not know which files or terms matter before starting work.
catchup
Restore context after /clear by summarizing recent work and project state.
context-dump
Sync 7 days of GitHub activity (commits, PRs, issues, reviews) into a structured context dump. Optionally pull from Slack, GDrive, or Asana if configured. Use at the start of a session to get fully caught up before coding.
learning
Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.
session
Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (context compression).