Update Agent Context Skill for Claude
Update agent context files for this project. Use when the user invokes /update-agent-context, asks to "update agent docs", "update CLAUDE.md", "update AGENTS.md", "add to agent_docs", "record a correction", or mentions updating context for a specific topic.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/Automattic/vip-go-mu-plugins-built --skill update-agent-contextThe instruction itself
5 sections, as written by the authorUpdate Agent Context
Updates any part of the agent instruction layer: AGENTS.md, CLAUDE.md, CLAUDE.local.md,
agent_docs/, agent_docs_local/, or agent_docs/MEMORY/.
Accepts an optional topic — e.g. /update-agent-context testing or /update-agent-context linting.
If no topic is given, infer from the current task context.
What to Update
| File / Folder | When |
| ------------------------------- | -------------------------------------------------------------------- |
| AGENTS.md | Always-run instructions changed |
| CLAUDE.md / CLAUDE.local.md | Discovery or setup instructions changed |
| agent_docs/<topic>.md | Stable pattern learned — would have saved time if documented earlier |
| agent_docs_local/<topic>.md | Machine-specific override or local workaround |
| agent_docs/MEMORY/<TOPIC>.md | Mistake made and correct approach found — record immediately |
Two-Layer Rule
AGENTS.mdandagent_docs/are universal — fully self-contained, no global Claude assumptionsCLAUDE.md,CLAUDE.local.md,agent_docs_local/are personal Claude layer — may reference
developer machine config
Rules
- Update at the same time as the code change, not after
- Keep entries actionable — commands, not prose
agent_docs/is for stable patterns;MEMORY/is for corrections and gotchas- Prefer editing an existing file over creating a new one
- Run prettier after editing:
npx prettier --write AGENTS.md CLAUDE.md CLAUDE.local.md agent_docs/*.md agent_docs_local/*.md 2>/dev/null
Memory Entry Format
- `<wrong thing>` is wrong. Correct: <right thing>.
One bullet per correction. Specific, terse, immediately usable.
Other skills for the same job
different authors, same section of the catalogue
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
How to use it
Take automattic/update-agent-context from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.