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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.00856 |
| Opus 5.5 | $0.00028 | $0.00342 |
| Sonnet 5.5 | $0.00014 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00086 |
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 19d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lane memory
Facts that cannot be derived from git or the code documentation (docs/). Laws from the SMA 5.6.1 drawing.
Where it lives. One memory per project on the BB hub (Lane Pilot's database), whatever machine the session
runs on: lane-memory write, search, context and CORE go through bb plugin rpc call lane-pilot session_memory_*. Without a connection a write waits in .cls/memory-outbox/ (lane-memory flush sends it).
.agents/memory/*.md files are not written any more; sensitive records stay local in .cls/local-memory.
LANE_MEMORY_HUB=off keeps the old local corpus.
Lessons. A correction or a landmine is a rule, not a file line:
lane-memory lesson "<one imperative rule>" --for pm|writer|both [--always] --evidence "<run/test/date>" (inside a Lane Pilot PM chat the tool lane_pilot_lesson does the same: rule, audience pm, writer or both — required, always optional).
--for pm — planning, task contracts, reviewing reports, merging, deploying: writers never get it. --for writer —
how code is edited and checked inside one task. --always only for a rule that holds for every writer task whatever
it changes (how to run or read any command); otherwise System One gives it to the tasks it fits. The hub merges
repeats, keeps at most 12 rules in force on trial, retires unused ones and lets at most 30 wait. Never append to
.agents/LESSONS.md.
Inside a Lane Pilot chat (
LANE_PILOT_AGENT_TYPEset / toolslane_pilot_*present) the hub is already on: read withlane_pilot_memory_contextorlane-memory search|context, write a lesson withlane_pilot_lesson. Do not create.agents/memory/files or drafts there, and do not call agentmemory tools (memory_save,memory_smart_search): that would start a second memory.
Memory-maintainer stage: when the host gives you an accepted task and asks for a JSON array of memory candidates, answer with that array only; do not run
lane-memory, do not edit files.
Info
What ships with it
2 files 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.
- 19d ago Changed · -44 lines · +2 tokens per session 2f1f56e949c9
- 20d ago Changed · +14 lines · +10 tokens per session b2b7e735aa57
- 25d ago Changed 914fc737afbd
- 1mo 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 (124 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 856 once invoked, about $0.0003 per session on Opus 5.5. 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
catchup
Restore context after /clear by summarizing recent work and project state.
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).
recall
Post-compaction context recovery. Reconstruct working context from session transcripts using MCP tools or CLI. Use when user says "recall", "recover context", "what was I doing", "after compaction", "lost context", or when context has been compacted and needs reconstruction.
vault
Context vault operations: read/update todos, add log entries, search vault content, read strategy/project docs, update project files. Use when user says "vault", "add todo", "update todos", "log entry", "search vault", "check todos", "context vault", "add to log", or any operation on a personal context vault.
session-learn
Meta-skill that analyzes past session transcripts to derive new skills, CLAUDE.md rules, and MEMORY.md entries from real usage patterns. Use when Use when user says "session learn", "derive skills", "learn from sessions", "what patterns", "analyze sessions", "extract rules", "what should I add to claude md", "improve…