Agent context update

Skill lx-wnk/skills/skills/agent-context-update

Update Agent-Context to the latest version — refreshes shared infrastructure files while preserving all project-specific configuration, memory, and skills. Use this skill whenever the user asks to update Agent-Context, upgrade Agent-Context, sync Agent-Context, or says things like "update agent-context", "get latest agent-context", "refresh context files", "sync agent infrastructure". Also use when the user wants to check if a newer Agent-Context version is available.From its SKILL.md

Install

npx -y skills add lx-wnk/skills --skill agent-context-update

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.0 KB, as published. Nobody here has run it

Update Agent-Context

Update shared Agent-Context files to the latest version without touching project-owned content.

Examples

# Update to latest version
/agent-context-update

# Update to a specific version
/agent-context-update v0.3.0

Prerequisites Check

Before starting, verify Agent-Context is installed:

cat .agent-context/.agent-context-version 2>/dev/null

If the file does not exist: STOP. Tell the user Agent-Context is not initialized and suggest using the init skill instead.
If the file exists: note the current version and proceed.

Update

Resolve the target release tag first, then fetch the setup prompt pinned to that tag and follow its instructions. Fetching a specific release tag (never the mutable main branch) is deliberate: the tag is pinned for the whole run, so the fetched prompt is fixed between resolution and execution, and it changes only when a new release is published — unlike main, which every push mutates. (Full tamper-resistance additionally requires tag/release protection on the source repo.)

# Resolve target version: explicit $ARGUMENTS, else latest release (never mutable `main`)
TAG="${ARGUMENTS:-$(gh api repos/lx-wnk/Agent-Context/releases/latest --jq .tag_name)}"
curl -fsSL "https://raw.githubusercontent.com/lx-wnk/Agent-Context/${TAG}/.prompts/setup-prompt.md"

The setup prompt auto-detects UPDATE mode (because .agent-context-version exists). Follow the fetched instructions, subject to the consent gates in Trust Boundary & Consent below. The setup prompt handles:

Version check — fetch latest release, compare with current version
Shared file refresh — overwrite only shared files (agent-startup.md, layer0-agent-workflow.md, base-principles.md, plugins.json)
New templates — create any new template files introduced in the new version (without overwriting existing ones)
Agent sync — update shared agents where they already exist
Plugin sync — merge new plugins into .claude/settings.json
Compatibility check — scan for deprecated patterns and suggest fixes

If $ARGUMENTS contains a version tag, use that version instead of latest.

Trust Boundary & Consent

This skill fetches a remote setup prompt (pinned to a release tag, see above) and follows it. That prompt performs trust-expanding operations: it can update transitive agents, merge plugins, and modify .claude/settings.json. Treat these as privileged, even though this is an update into an already-initialized project.

Before any step that updates agents (4), merges plugins (5), or writes to .claude/settings.json, stop and get explicit user confirmation — since this merges into an existing configuration, list exactly what will be ADDED or CHANGED against the current state, then wait for a yes. Never install transitive agents or merge plugins silently. If the user declines a step, skip it and continue with the rest of the update.

What is NEVER touched

AGENTS.md, layer1-bootstrap.md, layer2-project-core.md, layer3-guidebook.md
All files in memory/ and skills/
decisions.json
.claude/settings.json (only additive merges)

After Update

Report:

Previous version → new version
Files updated
Any new templates created
Compatibility warnings (if any)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most context ai engineering skills give

Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06

Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
Use the least powerful model capable of the taskin 33 of 1328, across 26 files
Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
Perform a task review after each implementationin 31 of 1328, across 24 files
Extract all tasks and context from the planin 29 of 1328, across 20 files
Provide full task text to subagentsin 28 of 1328, across 20 files
Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files

Said here and by no other author read

Verify if Agent-Context is already initialized
Resolve target version using release tags
Fetch setup prompt from pinned release tag
Follow instructions in the fetched setup prompt
Request user confirmation before merging plugins
Skip steps if user declines consent

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.