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 agentmods add skills/yushui2022/mathmodel-skill/context-memory-keepernpx skills add yushui2022/MathModel-Skill --skill context-memory-keepergit clone --depth 1 https://github.com/yushui2022/MathModel-SkillWrote 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/yushui2022/mathmodel-skill/context-memory-keeper)<a href="https://agentmods.dev/skills/yushui2022/mathmodel-skill/context-memory-keeper"><img src="https://agentmods.dev/badge/skills/yushui2022/mathmodel-skill/context-memory-keeper.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01380 |
| Opus 5 | $0.00018 | $0.00690 |
| Sonnet 5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
context-memory-keeper 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Memory Keeper
全局流程协作约束（长对话防漂移）
- 本 skill 不得作为孤立入口。用户要求完整论文、生成 Word、继续流程或不确定阶段时，先回到
paper-workflow-orchestrator判断当前 S0-S8 阶段。 - 启动或继续本 skill 的正式任务前，必须运行：
python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --skill context-memory-keeper - 如果输出
[WORKFLOW FAIL]或报告status != "PASS"，停止本 skill，按paper_output/qa/workflow_guard_report.json的失败项回补前置阶段，不得凭记忆继续。 - 本 skill 只写入自己契约范围内的
paper_output/产物；完成后必须回到paper-workflow-orchestrator判断下一步，并用context-memory-keeper记录已完成产物、阻塞项和下一步。 - 长对话中如果上下文变长、阶段不确定或用户分开调用 skill，先运行：
再读取python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --statuspaper_output/qa/workflow_guard_report.json、paper_output/preflight_report.json、paper_output/input_manifest.json、paper_output/results/run_manifest.json和本 skill 的上游 JSON 契约，按报告里的recommended_skill与next_action继续。 - 继续流程前，必须把
paper_output/context/workflow_memory.json视为长期断点记录；若其中的current_step、next_step、recommended_skill与workflow_guard.py --status不一致，以 guard 报告为准。 - 每次完成本 skill 的产物后，先回到
paper-workflow-orchestrator或运行workflow_guard.py --status，再更新 workflow memory：
更新后读取python .claude/skills/context-memory-keeper/scripts/update_workflow_memory.pypaper_output/context/workflow_memory.json/.md，确认下一步和推荐 skill 已记录。
执行契约
- 上游输入：当前赛题约束、模型路线、数据源、图表路径、QA 结论、用户新增偏好和流程断点。
- 必须输出：更新后的
memoryskill.md；当短期工作台过长时，将旧任务摘要归档到memory_archive.md。 - 下游交接：其他 skill 在复杂任务开始前读取
memoryskill.md，避免遗忘当前模型路线、数据来源和用户要求。 - 推荐下一步：完成记忆更新后回到调用它的当前 skill；若目标是完整论文，回到
paper-workflow-orchestrator判断后续阶段。 - 失败回退：若无法安全更新记忆文件，应在本轮回复中明确保留关键结论，并提示后续手动补写到记忆文件。
Description
此 Skill 维护双层记忆结构，旨在解决模型上下文遗忘问题，同时保持上下文窗口的整洁。
Files Structure
Executable Workflow Memory
- After
workflow_guard.py --statusor after a skill handoff, run:python .claude/skills/context-memory-keeper/scripts/update_workflow_memory.py - The script reads
paper_output/qa/workflow_guard_report.jsonplus key workflow artifacts and writes:paper_output/context/workflow_memory.jsonpaper_output/context/workflow_memory.md
- Long conversations and resumed sessions should read
workflow_memory.jsonbefore relying on chat history.
What ships with it
3 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.
- 4d ago First seen · 78 lines · 36 tokens per session scan A 32621f9c3740
context-memory-keeper is a skill published in the GitHub repository yushui2022/MathModel-Skill (340 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,380 once invoked, about $0.0002 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…