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 IvanYangYangXi/artclaw_bridge --skill artclaw-memorygit clone --depth 1 https://github.com/IvanYangYangXi/artclaw_bridgeWrote 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/ivanyangyangxi/artclaw_bridge/artclaw-memory)<a href="https://agentmods.dev/skills/ivanyangyangxi/artclaw_bridge/artclaw-memory"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/artclaw-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/ivanyangyangxi/artclaw_bridge/artclaw-memory"><img src="https://agentmods.dev/badge/skills/ivanyangyangxi/artclaw_bridge/artclaw-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00098 | $0.01997 |
| Opus 5 | $0.00049 | $0.00999 |
| Sonnet 5 | $0.00020 | $0.00399 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
artclaw-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 12d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArtClaw 记忆管理
记住用户偏好、操作历史、项目规范、踩坑经验,管理和维护 ArtClaw 的记忆系统。
何时读取记忆 (必须遵守)
1. 对话开始时 — 自动注入 (已实现,无需手动)
Memory Briefing 在 bridge 层自动注入到首条消息,包含团队记忆和个人记忆。
2. 反复出错时 — 主动搜索 (强制)
当同一类操作连续失败 2 次以上时,必须主动搜索记忆寻找解决方案:
from core.memory_store import get_memory_store
mm = get_memory_store()
if mm:
# 搜索个人记忆
hints = mm.manager.search("关键词", tag="crash", limit=3)
hints += mm.manager.search("关键词", tag="pattern", limit=3)
# 搜索团队记忆
team_hints = mm.manager.search_team_memory("关键词", limit=3)
3. 高风险操作前 — 主动检查 (建议)
执行删除、批量修改、材质替换、导入导出等操作前:
check = mm.manager.check_operation(tool="工具名", action_hint="操作描述")
# 如果有 crash_rules 或 warnings,告知用户风险
何时写入记忆 (必须遵守)
核心原则: 只记"付出代价的经验"
- 一次性成功的操作不记录
- 多次尝试才成功的经验才值得记录
1. 多次尝试后成功 — 提炼规则 (强制)
当你经过 2 次以上尝试或修改才正确完成一个操作时,必须提炼规则并记录:
mm.manager.record(
key="pattern:简短描述",
value="精炼的规则(一句话说清楚问题和解法)",
tag="pattern",
importance=0.8,
source="retry_learned"
)
规则质量要求:
- 一句话说清楚:什么情况 + 正确做法
- 示例: "MaterialExpressionMultiply 的 A/B 输入必须显式连接,留空会报错"
- 不要记录过程细节,只记最终结论
2. 用户纠正后 — 提炼教训 (强制)
当用户指出错误("不对"/"错了"/"重做"等)并经过修正后,主动提炼教训:
mm.manager.record(
key="pattern:被纠正的问题描述",
value="正确的做法和原因",
tag="pattern",
importance=0.8,
source="user_correction"
)
3. 发现反直觉行为 — 记录陷阱 (强制)
当发现 API 行为与文档/直觉不符时:
mm.manager.record(
key="pattern:API或行为描述",
value="实际行为和正确用法",
tag="pattern",
importance=0.9,
source="gotcha"
)
4. 崩溃/严重错误 — 记录规则 (强制)
mm.manager.record_crash(
tool="工具名",
action="操作名",
params_summary="参数摘要",
error="错误信息",
root_cause="根因分析(一句话)",
avoidance_rule="避免规则(一句话)",
severity="high" # low/medium/high/critical
)
5. 用户明确说"记住" — 直接存储
mm.manager.record(
key="合适的key",
value="用户要记住的内容",
tag="preference", # 或 convention/fact
importance=0.7
)
不要记录的内容
- 纯查询操作(列出 Actor、获取属性等)
- 一次性简单操作(移动物体、改个颜色)
- 已经在团队记忆中存在的规则(避免重复)
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.
- 12d ago First seen · 235 lines · 98 tokens per session scan A 3429bd233232
artclaw-memory is a skill published in the GitHub repository IvanYangYangXi/artclaw_bridge (35 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,997 once invoked, about $0.0005 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
dcc-mcp-core
Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…