Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .claude/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .agents/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .cursor/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .gemini/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .github/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "context-memory-keeper" agent skill from https://github.com/yushui2022/MathModel-Skill/tree/standard/packages/trae/.trae/skills/context-memory-keeper into .opencode/skills/context-memory-keeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-memory-keeper", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
context-memory-keeper
GitHub stars
452
Used in
1 other repo
Token cost
~893 tokens
SKILL.md length
219 words
Files
4 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
MIT
At a glance
Maintains a two-layer persistent memory for a math-modeling paper workflow: long-term rules plus a short-term workbench, with finished tasks archived.
Works in 2 steps: memoryskill.md (Active Memory) → memory_archive.md (Archive)
Resuming a long paper-writing workflow where context has started to drift
SKILL.md covers 全局流程协作约束（长对话防漂移）, 执行契约, Description and Files Structure, plus 4 more sections
Runs Python scripts from its folder; calls python
What it does
The skill keeps two files. memoryskill.md is the active memory: long-term principles such as user preferences, role settings and global constraints, which are mostly read-only, and a short-term workbench with current task state, variables, steps in progress and an index of external literature and data, which changes often. memory_archive.md receives summaries of old tasks when the workbench grows too long.
It sits inside a larger paper-writing workflow. Before formal work it runs a workflow_guard.py check from the paper-workflow-orchestrator skill and stops if the report is not a pass, rather than continuing from memory. After outputs are completed it runs scripts/update_workflow_memory.py, which reads the guard report and key artifacts and writes workflow_memory.json and workflow_memory.md under paper_output/context. Long or resumed sessions read workflow_memory.json before trusting chat history, and the guard report wins when the two disagree.
Other skills read memoryskill.md before complex tasks so they keep the model route, data sources and your requirements in view. If the memory files cannot be updated safely, the agent keeps the key conclusions in its reply and asks for a manual note later. The skill text is mostly in Chinese.
When your agent uses it
Resuming a long paper-writing workflow where context has started to drift
Archiving finished tasks so the active memory stays short
Recording completed outputs, blockers and next steps after a skill finishes
Example prompts
“Update the workflow memory with what we finished and what blocks the next stage.”
“Archive the completed data-cleaning tasks out of the active memory.”
“Read the active memory before we continue with the model section.”
Requirements
Python, for scripts/update_workflow_memory.py
The paper-workflow-orchestrator skill and its workflow_guard.py script
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
1memoryskill.md (Active Memory)
2memory_archive.md (Archive)
What it can do on your machine
Read from SKILL.md and the folder at commit 7712876. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Context Memory Keeper loads about 893 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 219 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~43
When it runs· the whole SKILL.md, loaded when a task matches
~893
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/context-memory-keeper/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
context-memory-keeper
description
Manages persistent memory. Invoke to read active context or archive old tasks. Structure: Long-term Principles (Rules) + Short-term Workbench (Tasks).
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in yushui2022/MathModel-Skill, which our catalogue first saw on October 7, 2026.
Context Memory Keeper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Context Memory Keeper compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Context Memory Keeper this skillyushui2022/MathModel-Skill
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.
Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.
Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.
Repairs one failing section of a mathematical modeling paper from the repair queue, or builds a legacy or quickstart scaffold when you ask for one by name.
Finds authoritative public data sources for modeling tasks, prefers official APIs and bulk downloads, and outputs a reproducible fetch and cleaning plan with citations.
Maintains a two-layer persistent memory for a math-modeling paper workflow: long-term rules plus a short-term workbench, with finished tasks archived. The skill keeps two files.md is the active memory: long-term principles such as user preferences, role settings and global constraints, which are mostly read-only, and a short-term workbench with current task state, variables, steps in progress and an index of external literature and data, which changes often.
When should I use Context Memory Keeper?
Context Memory Keeper fits situations like: resuming a long paper-writing workflow where context has started to drift; archiving finished tasks so the active memory stays short; recording completed outputs, blockers and next steps after a skill finishes.
How do I install Context Memory Keeper in Claude Code?
Run `npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a claude-code`. Or copy the skill folder (packages/trae/.trae/skills/context-memory-keeper in yushui2022/MathModel-Skill) into .claude/skills/context-memory-keeper in your project. Claude Code loads it when a task matches its description.
How do I install Context Memory Keeper in Codex?
Run `npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a codex`. Or copy the skill folder (packages/trae/.trae/skills/context-memory-keeper in yushui2022/MathModel-Skill) into .agents/skills/context-memory-keeper in your project. Codex loads it when a task matches its description.
Can I use Context Memory Keeper in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yushui2022/MathModel-Skill --skill context-memory-keeper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-memory-keeper, .gemini/skills/context-memory-keeper, .github/skills/context-memory-keeper and .opencode/skills/context-memory-keeper in your project.
What does Context Memory Keeper need to run?
Going by SKILL.md and its folder, Context Memory Keeper needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python, for scripts/update_workflow_memory.py; The paper-workflow-orchestrator skill and its workflow_guard.py script.
Does Context Memory Keeper access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Context Memory Keeper safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Context Memory Keeper use?
Context Memory Keeper is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Context Memory Keeper use?
About 893 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Context Memory Keeper?
Skills that share tags, products or a category with Context Memory Keeper: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Beads Task Memory (gastownhall/beads, 28k stars), Session History Search (slopus/happy, 24k stars) and Memori Long-Term Memory (MemoriLabs/Memori, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Memory Keeper?
yushui2022 (a GitHub user) maintains it in yushui2022/MathModel-Skill, which has 452 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: yushui2022/MathModel-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
