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 murray17/rovai-ai --skill memory-stewardshipgit clone --depth 1 https://github.com/murray17/rovai-aiWrote 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/murray17/rovai-ai/memory-stewardship)<a href="https://agentmods.dev/skills/murray17/rovai-ai/memory-stewardship"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/memory-stewardship/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/murray17/rovai-ai/memory-stewardship"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/memory-stewardship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.00560 |
| Opus 5 | $0.00044 | $0.00280 |
| Sonnet 5 | $0.00017 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
memory-stewardship 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 10d 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
共同记忆维护
只保留会影响未来协作的稳定信息。当前事实、用户最新指令和项目权威来源始终高于 Memory。
判断标准
候选内容应当同时满足：
- 当前任务结束后仍有价值；
- 来自用户明确表达或真实经历支持的经验；
- 会改变未来协作行为，而不只是复述发生过的事情；
- 能写成一条独立、原子的偏好、约定或经验；
- 不应由 Task、项目文档、代码、历史记录或权限系统承担；
- 不包含敏感信息或无依据的人格判断。
不满足这些条件时不写入。
流程
- 读取 Authority 与安全，确认候选内容适合长期保留。
- 把候选压缩成一条原子的未来协作路标。
- 读取 Scopes、Kind 与方向，选择最小适用范围。
- 读取 View、广泛回忆与最小写入，检查相关现有 Memory。
- 只选择一个结果：已有等价内容则停止；已有内容需要纠正则修订；确有新价值则新增；无法确定则停止。
- 写入前读取 正文与 Retrieval Keys，完成一次最小更新。
- 根据实际结果准确说明已经生效、等待用户决定或未写入。
用户要求删除、停用、恢复或修改不属于当前队员权限的 Memory 时，不用相反正文模拟操作；说明需要由用户在记忆管理中完成。
边界
- 一次只处理一条原子信息，不连续写多条“以防万一”。
- 不在会话结束时进行全面记忆扫描。
- 不把临时日期、路径、分支、进度和一次性阻塞写成长期记忆。
- 不把搜索摘要、缓存或旧版本当作当前权威正文。
- 写入失败或结果不确定时，不声称已经保存。
What ships with it
6 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.
- 10d ago First seen · 42 lines · 87 tokens per session scan A 89917e8b9ad9
memory-stewardship is a skill published in the GitHub repository murray17/rovai-ai (60 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 560 once invoked, about $0.0004 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
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.
powercontext
Use PowerContext for durable memory, cross-session continuity, and reviewed Experience or Skill artifacts.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.