Memory Manage
Bootstrap, sync, and housekeeping the ai-context/ memory layer so coding agents retain stack, architecture, conventions, and known issues across sessions.
Overview
memory-manage is an agent skill most often used in Build (also Ship and Operate) that initializes, updates, and maintains the ai-context/ procedural memory layer for long-running agent sessions.
Install
npx skills add https://github.com/fearovex/claude-config --skill memory-manageWhat is this skill?
- Three procedural modes: init, update, and maintain detected from slash commands or natural triggers
- Init generates 5 core ai-context/ files from repo inventory (stack, architecture, conventions, known-issues, plus README
- Update mode records session work and syncs memory after shipping changes
- Maintain mode prunes stale entries and keeps ai-context/ readable over long projects
- Unified entry via /memory-init, /memory-update, /memory-maintain
- 3 modes: init, update, maintain
- 5 core ai-context/ files targeted on init (stack, architecture, conventions, known-issues, plus generated context from i
Adoption & trust: 1 installs on skills.sh; 1 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
Your coding agent forgets stack versions, conventions, and open issues every session because nothing durable documents the project for AI readers.
Who is it for?
Solo builders standardizing on ai-context/ who want one skill to create, refresh, and clean agent-facing project memory without manual copy-paste.
Skip if: Repos that already use a different enforced memory system you will not migrate, or one-off chats with no intention to reuse agent context.
When should I use this skill?
/memory-init, /memory-update, /memory-maintain, initialize memory, update memory, maintain memory, memory housekeeping, or clean ai-context.
What do I get? / Deliverables
ai-context/ holds current stack, architecture, conventions, and known issues files, with maintain mode keeping them accurate after init or session updates.
- Populated or refreshed ai-context/*.md memory files
- Maintain-mode cleanup summary of pruned or merged sections
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
First shelf is Build agent-tooling because init/update modes establish the persistent context files agents read during implementation. Agent-tooling is where procedural memory files (stack, architecture, conventions) directly shape how Claude/Cursor behave in the repo.
Where it fits
Run init mode on a greenfield SaaS repo so the agent knows versions and folder conventions before feature work.
After a security fix lands, run update mode so known-issues.md reflects the remediation for the next review pass.
Quarterly maintain mode removes resolved bugs and outdated stack pins from ai-context/ before a refactor sprint.
How it compares
Skill package for repo-local procedural memory—not an MCP server and not ad-hoc CLAUDE.md edits without a maintenance ritual.
Common Questions / FAQ
Who is memory-manage for?
Indie developers and small teams using agentic IDEs who want durable ai-context/ files instead of re-explaining the codebase each session.
When should I use memory-manage?
Use it in Build when onboarding agents to a new repo (init), in Ship after meaningful merges or releases (update), and in Operate when memory files grow stale or contradictory (maintain)—triggered by /memory-init, /memory-update, or /memory-maintain.
Is memory-manage safe to install?
It reads and writes files under your project; check the Security Audits panel on this page and review diffs before committing generated ai-context/ content that may summarize internal paths or issues.
SKILL.md
READMESKILL.md - Memory Manage
# memory-manage > Unified management of the ai-context/ memory layer. Three modes: init, update, maintain. **Triggers**: `/memory-init`, `/memory-update`, `/memory-maintain`, initialize memory, update memory, maintain memory, memory housekeeping, clean ai-context --- ## Mode Detection Determine the mode from the invocation: - `/memory-init` or "initialize memory" or "generate ai-context" → **init mode** - `/memory-update` or "update memory" or "sync memory" or "record session" → **update mode** - `/memory-maintain` or "maintain memory" or "memory housekeeping" or "clean ai-context" → **maintain mode** --- ## Mode: init > Creates the 5 core ai-context/ files from scratch by reading the project. **Use when**: Project has no `ai-context/` yet, or you want to regenerate from scratch. ### Process 1. **Project inventory**: Read configuration files, folder structure, README, representative source files, tests, CI/CD configs. 2. **Generate files**: - `ai-context/stack.md` — tech stack, versions, key tools - `ai-context/architecture.md` — architectural decisions and rationale - `ai-context/conventions.md` — naming patterns, code conventions - `ai-context/known-issues.md` — known bugs, tech debt, gotchas - `ai-context/changelog-ai.md` — empty, ready for session entries 3. **Feature stubs**: Scan for bounded contexts (directories with domain logic). Create `ai-context/features/_template.md` and stub files for discovered domains. 4. **Report**: List files created and coverage summary. --- ## Mode: update > Incrementally updates ai-context/ with work done in the current session. **Use when**: After completing significant work (SDD cycles, architecture changes, bug fixes). ### Process 1. **Analyze session**: Review what changed — files created/modified, decisions made, bugs fixed, conventions established. 2. **Update relevant files**: - `ai-context/stack.md` — new dependencies, version changes - `ai-context/architecture.md` — new decisions, pattern changes - `ai-context/conventions.md` — new naming patterns, style changes - `ai-context/known-issues.md` — new issues found, resolved issues marked - `ai-context/changelog-ai.md` — append entry with date, summary, files affected - `ai-context/features/<domain>.md` — update if relevant domain was touched 3. **Preserve**: Never overwrite `[manual]` sections. Only update `[auto-updated]` markers. --- ## Mode: maintain > Periodic housekeeping: archive old entries, separate resolved issues, detect gaps. **Use when**: changelog-ai.md is long (30+ entries), known-issues has resolved items, or at the start of a new project phase. ### Process 1. **Changelog archival**: If `changelog-ai.md` has more than 30 entries, move older entries to `changelog-ai-archive.md`. 2. **Known-issues cleanup**: Move resolved items from `known-issues.md` to `known-issues-archive.md`. 3. **Index generation**: Create/update `ai-context/index.md` listing all ai-context/ files with one-line descriptions. 4. **Gap detection**: Check if CLAUDE.md references ai-context/ files that don't exist. Report gaps. 5. **Dry-run first**: Present all proposed changes, require user confirmation before applying. --- ## Rules - Init mode MUST NOT run if ai-context/ already exists — warn and suggest update mode instead - Update mode MUST NOT create new core files — only modify existing ones - Maintain mode MUST present dry-run before any destructive action (archival, moves) - All modes are read-heavy, write-light — the goal is accurate, concise documentation - Never overwrite `[manual]` sections in any file - Feature file updates follow the format defined in `skills/feature-domain-expert/SKILL.md`