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 YangsonHung/awesome-agent-skills --skill tree-ring-memory-cngit clone --depth 1 https://github.com/YangsonHung/awesome-agent-skillsWrote 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/yangsonhung/awesome-agent-skills/tree-ring-memory-cn)<a href="https://agentmods.dev/skills/yangsonhung/awesome-agent-skills/tree-ring-memory-cn"><img src="https://agentmods.dev/badge/skills/yangsonhung/awesome-agent-skills/tree-ring-memory-cn/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/yangsonhung/awesome-agent-skills/tree-ring-memory-cn"><img src="https://agentmods.dev/badge/skills/yangsonhung/awesome-agent-skills/tree-ring-memory-cn.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 | $0.00043 | $0.01275 |
| Opus 5.5 | $0.00017 | $0.00510 |
| Sonnet 5.5 | $0.00009 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
tree-ring-memory-cn 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tree Ring Memory
Overview
使用本技能把 Tree Ring Memory 当作具备生命周期意识的 AI Agent 记忆层来操作。它适合保存长期有用的决策、经验、警告、项目约定、用户偏好和未来种子,而不是保存完整聊天记录,也不是后台自动抓取器。
核心思想是让 Agent 记忆有意地老化:
- 仍在进行的工作可以保留较多细节
- 较旧经验应压缩成稳定摘要
- 重要失败和警告应保持可见
- 持久偏好和项目事实应成为高置信记忆
- 尚未确认的后续想法应与事实分开
- 敏感信息应默认阻止、脱敏或遗忘
何时使用
在以下场景使用本技能:
- 用户要求记住、召回、合并、脱敏或遗忘。
- 当前任务依赖过去的项目决策、偏好或警告。
- Agent 正在开始或恢复一个带有 Tree Ring Memory 或项目本地
.tree-ring目录的仓库。 - 测试、事故、PR、基准、评审或运行记录产生了对未来有用的经验。
AGENTS.md、DOX 或 Revolve 等来源文档包含应汇总进记忆的长期指导。- Agent 需要在高风险改动前审计已保存的记忆。
不要使用
以下场景不要把本技能作为主要指南:
- 任务结束后就应消失的短期草稿。
- 原始思维链或隐藏推理。
- 密钥、凭据、令牌、私钥、支付信息或其他敏感值。
- 保存完整对话,而不是简洁经验或决策。
- 把未经验证的说法当作持久项目事实。
- 替代来源文档、测试、Issue、PR 或发布记录。
使用说明
当 Tree Ring Memory 能改善连续性时,按下面的流程执行。简单任务中只做窄范围召回,并且只有经验明显具备长期价值时才写入记忆。高风险任务中应加入来源检查、证据化记录和收尾复盘。
工作流程
- 当历史上下文可能影响任务时,先召回再行动。
- 优先使用窄范围、项目级查询,避免泛泛的全局召回。
- 如果存在来源文档,必须直接读取;记忆不能替代
AGENTS.md、项目文档、测试、Issue、PR 或发布记录。 - 只保存未来确实有帮助的简洁经验、决策、警告和偏好。
- 如果经验来自经过审查的运行、评估、检查点、事故、分支、PR、Issue 或测试产物,优先使用证据化记录。
- 对过时或敏感记忆执行脱敏、替换或删除,不要保留已知错误的上下文。
命令参考
先查看本地帮助,确保命令与当前安装版本一致:
tree-ring --help
tree-ring evidence --help
tree-ring dox sync --help
tree-ring revolve sync --help
如果项目有本地 Tree Ring 配置,先读取 .tree-ring/SKILL.md 和 .tree-ring/CLI.md,不要直接假设全局配置适用于当前仓库。需要显式指定项目存储时,使用本地 root:
tree-ring --root .tree-ring recall --query "release decisions"
tree-ring --root .tree-ring evidence --help
写入来源适配器摘要前先使用 dry-run:
tree-ring dox sync --source-root . --dry-run
tree-ring revolve sync --source-root revolve --dry-run
tree-ring integrations scan --source-root .
只有当摘要简洁、有用、带来源且隐私安全时,才执行实际写入。
年轮模型
用年轮模型判断保留强度:
cambium:当前活跃任务上下文outer:近期决策和经验inner:较旧的压缩项目知识heartwood:高置信、长期稳定的事实和偏好scar:重要失败、回归、被否定方案和警告seed:未解决想法、假设和后续事项
不要把证据薄弱的内容提升到 heartwood。在用户确认或证据足够强之前,优先使用 outer 或 seed。
隐私守门规则
永远不要保存:
- 密钥、凭据、令牌、私钥或支付信息
- 原始思维链
- 临时草稿
- 未验证却被当作持久事实的说法
- 未经用户明确指示的敏感健康、财务、法律或个人标识信息
- 超出短摘录范围的受版权保护文本
如果有用记忆包含敏感材料,只保留足够避免重复错误的脱敏操作摘要。
收尾清单
结束有意义的工作前,检查:
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.
- 1mo ago First seen · 122 lines · 43 tokens per session scan A a51fd5902c5a
tree-ring-memory-cn is a skill published in the GitHub repository YangsonHung/awesome-agent-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,275 once invoked, about $0.0002 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
docs-context
Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions)…
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
claude-md-updater
Scans the session for durable lessons and workflows, then proposes scoped project instruction updates. Use for save this lesson or add to context.