Context Memory
Triggers automatically for multi-step agent loops to prevent context window exhaustion.
Skill by sh4lu-z
Chalk Labs
Need help deploying Context Memory?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sh4lu-z-context-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/context-memory
What's inside
- Skill name
Context Memory- Description
- Triggers automatically for multi-step agent loops to prevent context window exhaustion.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Context Memory" does not match folder "context_memory"
Files (1)
- SKILL.md
SKILL.md (first lines)
1. ROLLING CONTEXT (STATE MANAGEMENT): To prevent filling up your context window during long tasks, you only remember your Scratchpad. After your thought block, you MUST maintain a concise summary of your progress. Output this inside `<SCRATCHPAD>` tags. Format: <SCRATCHPAD> Goal: [Overall goal] Done: [What was just achieved] Next: [What needs to be done now] </SCRATCHPAD> CRITICAL: FORGET completed steps in your scratchpad once they are marked `[x]` in the project's brain folder `task.md` to save memory. Just say "Tasks 1-4 completed". Do not reprint old data.
From sh4lu-z/Syntiox-CORE, MIT.
More from sh4lu-z/Syntiox-CORE
- 0.622score
Semantic Codebase Search
sh4lu-z
Triggers when the user asks to find something conceptually in the codebase or search for code without knowing the exact file.
SkillAFreshness: A★ 10Claude Code +9 - 0.616score
Core Thinking
sh4lu-z
Always required.
SkillAFreshness: A★ 10Claude Code +9 - 0.611score
Task Management
sh4lu-z
Triggers for large projects, complex multi-step tasks, planning, and creating documentation.
SkillAFreshness: A★ 10Claude Code +9 - 0.591score
Document Processing
sh4lu-z
Use when the user asks to read, summarize, or extract data from PDF, Word, Excel, or CSV files.
SkillAFreshness: A★ 10Claude Code +9 - 0.591score
Developer & Git Assistant
sh4lu-z
Use when the user asks for coding help, debugging, git commands, version control, or project management.
SkillAFreshness: A★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 1, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sh4lu-z/Syntiox-CORE
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sh4lu-z
- 0.622score
Semantic Codebase Search
sh4lu-z
Triggers when the user asks to find something conceptually in the codebase or search for code without knowing the exact file.
SkillAFreshness: A★ 10Claude Code +9 - 0.616score
Core Thinking
sh4lu-z
Always required.
SkillAFreshness: A★ 10Claude Code +9 - 0.611score
Task Management
sh4lu-z
Triggers for large projects, complex multi-step tasks, planning, and creating documentation.
SkillAFreshness: A★ 10Claude Code +9 - 0.591score
Document Processing
sh4lu-z
Use when the user asks to read, summarize, or extract data from PDF, Word, Excel, or CSV files.
SkillAFreshness: A★ 10Claude Code +9 - 0.591score
Developer & Git Assistant
sh4lu-z
Use when the user asks for coding help, debugging, git commands, version control, or project management.
SkillAFreshness: A★ 10Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Context Memory running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Context Memory skill. Agent Mart. https://agentmart.dev/skills/sh4lu-z-context-memory (last updated 2026-10-24)