Memory Management
Maintain CLAUDE.md hot cache plus a memory/ knowledge base so your coding agent decodes internal names, acronyms, and deal shorthand like a teammate.
Overview
memory-management is a journey-wide agent skill that builds a two-tier CLAUDE.md and memory/ knowledge base—usable whenever a solo builder needs the agent to understand internal shorthand before committing to work.
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill memory-managementWhat is this skill?
- Two-tier system: CLAUDE.md hot cache (~30 people, ~30 terms) plus memory/ directory for full glossary and profiles
- Decodes shorthand requests (nicknames, acronyms, internal deal names) into explicit actions
- Structured memory layout: glossary.md, people/, projects/, context/ folders
- Goal stated for hot cache: cover ~90% of daily decoding needs
- Designed so Claude behaves as a workplace collaborator, not a generic chatbot
- ~30 people and ~30 terms targeted in CLAUDE.md hot cache
- Hot cache goal: cover ~90% of daily decoding needs
Adoption & trust: 4.4k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent treats internal nicknames, acronyms, and project codenames as nonsense, so every task starts with painful re-contextualization.
Who is it for?
Solo operators and micro-teams with dense internal vocabulary who live in Claude Code and want durable organizational memory.
Skip if: Anonymous open-source-only workflows with no stable team lexicon, or teams that already enforce everything through a formal CRM with MCP integration.
When should I use this skill?
Before relying on the agent for knowledge work that uses internal shorthand, acronyms, nicknames, or deal-specific language.
What do I get? / Deliverables
After structuring hot-cache and full memory files, the agent expands shorthand into precise people, deliverables, and project references before executing requests.
- CLAUDE.md hot-cache file
- memory/glossary.md and optional people/, projects/, context/ notes
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Expand 'PSR for oracle' into the right stakeholder and deal when writing a validation checklist.
Seed CLAUDE.md with top people and terms so implementation tasks reference correct Slack owners.
Decode campaign codenames when drafting lifecycle emails without re-pasting a org chart.
Interpret on-call shorthand for systems and teams during postmortem notes.
How it compares
Organizational decoder ring for your repo—not a vector database RAG product and not a one-shot brainstorming template.
Common Questions / FAQ
Who is memory-management for?
It is for indie builders and small teams whose agents must understand company-specific people, acronyms, and project aliases during daily knowledge work.
When should I use memory-management?
Use it whenever you onboard an agent on a codebase or business: during Build for CLAUDE.md setup, during Validate when scoping uses internal terms, during Grow for lifecycle comms, and during Operate when incidents reference systems by nickname.
Is memory-management safe to install?
Review the Security Audits panel on this page; memory files often hold people and deal details—treat memory/ as sensitive and avoid committing secrets—permissions are filesystem-focused.
SKILL.md
READMESKILL.md - Memory Management
# Memory Management Memory makes Claude your workplace collaborator - someone who speaks your internal language. ## The Goal Transform shorthand into understanding: ``` User: "ask todd to do the PSR for oracle" ↓ Claude decodes "Ask Todd Martinez (Finance lead) to prepare the Pipeline Status Report for the Oracle Systems deal ($2.3M, closing Q2)" ``` Without memory, that request is meaningless. With memory, Claude knows: - **todd** → Todd Martinez, Finance lead, prefers Slack - **PSR** → Pipeline Status Report (weekly sales doc) - **oracle** → Oracle Systems deal, not the company ## Architecture ``` CLAUDE.md ← Hot cache (~30 people, common terms) memory/ glossary.md ← Full decoder ring (everything) people/ ← Complete profiles projects/ ← Project details context/ ← Company, teams, tools ``` **CLAUDE.md (Hot Cache):** - Top ~30 people you interact with most - ~30 most common acronyms/terms - Active projects (5-15) - Your preferences - **Goal: Cover 90% of daily decoding needs** **memory/glossary.md (Full Glossary):** - Complete decoder ring - everyone, every term - Searched when something isn't in CLAUDE.md - Can grow indefinitely **memory/people/, projects/, context/:** - Rich detail when needed for execution - Full profiles, history, context ## Lookup Flow ``` User: "ask todd about the PSR for phoenix" 1. Check CLAUDE.md (hot cache) → Todd? ✓ Todd Martinez, Finance → PSR? ✓ Pipeline Status Report → Phoenix? ✓ DB migration project 2. If not found → search memory/glossary.md → Full glossary has everyone/everything 3. If still not found → ask user → "What does X mean? I'll remember it." ``` This tiered approach keeps CLAUDE.md lean (~100 lines) while supporting unlimited scale in memory/. ## File Locations - **Working memory:** `CLAUDE.md` in current working directory - **Deep memory:** `memory/` subdirectory ## Working Memory Format (CLAUDE.md) Use tables for compactness. Target ~50-80 lines total. ```markdown # Memory ## Me [Name], [Role] on [Team]. [One sentence about what I do.] ## People | Who | Role | |-----|------| | **Todd** | Todd Martinez, Finance lead | | **Sarah** | Sarah Chen, Engineering (Platform) | | **Greg** | Greg Wilson, Sales | → Full list: memory/glossary.md, profiles: memory/people/ ## Terms | Term | Meaning | |------|---------| | PSR | Pipeline Status Report | | P0 | Drop everything priority | | standup | Daily 9am sync | → Full glossary: memory/glossary.md ## Projects | Name | What | |------|------| | **Phoenix** | DB migration, Q2 launch | | **Horizon** | Mobile app redesign | → Details: memory/projects/ ## Preferences - 25-min meetings with buffers - Async-first, Slack over email - No meetings Friday afternoons ``` ## Deep Memory Format (memory/) **memory/glossary.md** - The decoder ring: ```markdown # Glossary Workplace shorthand, acronyms, and internal language. ## Acronyms | Term | Meaning | Context | |------|---------|---------| | PSR | Pipeline Status Report | Weekly sales doc | | OKR | Objectives & Key Results | Quarterly planning | | P0/P1/P2 | Priority levels | P0 = drop everything | ## Internal Terms | Term | Meaning | |------|---------| | standup | Daily 9am sync in #engineering | | the migration | Project Phoenix database work | | ship it | Deploy to production | | escalate | Loop in leadership | ## Nicknames → Full Names | Nickname | Person | |----------|--------| | Todd | Todd Martinez (Finance) | | T | Also Todd Martinez | ## Project Codenames | Codename | Project | |----------|---------| | Phoenix | Database migration | | Horizon | New mobile app | ```