VA24d

Align Agent — Development skill for Claude Code

Development community

ALIGN (Agent Line-Index Guard and Notices): keep coding agents' views of their files current (Claude Code, Codex, Gemini CLI, Cursor, Copilot CLI, OpenCode, Cline, MCP), and find stale edits in agent.

How to install Align Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open VA24d/align-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Align Agent does

ALIGN (Agent Line-Index Guard and Notices): keep coding agents' views of their files current (Claude Code, Codex, Gemini CLI, Cursor, Copilot CLI, OpenCode, Cline, MCP), and find stale edits in agent trajectories

Alternatives in Development

  • Third-party Notices — THE FOLLOWING SETS FORTH ATTRIBUTION NOTICES FOR THIRD PARTY SOFTWARE THAT MAY BE CONTAINED IN PORTIONS OF THI 94.7k ★
  • Octo Freeze — Restrict file edits to a specific directory boundary 2.8k ★
  • Portaljs Add Chart — Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal 2.3k ★

README

ALIGN: Agent Line-Index Guard and Notices

A coding agent edits files through what it last saw of them, and its own edits make those views out of date. A `sed -i`, a script, a formatter or `git checkout` changes a file the agent read, and nothing tells it; a later edit by line number or by remembered text then lands on the wrong lines, is applied twice, or misses. ALIGN keeps the agent's view current while it works, and finds these edits in recorded agent trajectories.

Keep your agent's view current

After every tool call, ALIGN appends to what the model sees the diff of each file it has seen that changed since, with current line numbers, a note for each stretch of lines that moved without being shown, and the remaining uses in other files of any definition a change removed or re-signatured. Before an in-place edit by line number (`sed`, `perl`, `awk`, `ed`, `ex`) on lines the model has not seen numbered as they are now, it refuses the command once and shows those lines. Nothing earlier in the conversation is rewritten, so the prompt cache is kept.

pip install git+https://github.com/VA24d/align-agent@v0.3.0   # the write-through engine itself uses only the standard library
Agent Set up
Claude Code /plugin marketplace add VA24d/align-agent, then /plugin install align-write-through@align-agent
Codex CLI, Gemini CLI, Cursor, GitHub Copilot CLI, OpenCode, Cline the config for your agent in `integrations/`
Any MCP client (Goose, Antigravity CLI, IDEs, ...) align-agent-mcp as an MCP server, with the built-in shell turned off (`integrations/mcp`)
Your own harness align-agent-wt: one JSON event on stdin, {"context": ...} or {"deny": ...} back; or from align_agent.writethrough import Session

In a 2,000-file repository a call takes well under 0.5 s; in Claude Code a call took about 0.1 s, Python start-up included.

To compute diffs, ALIGN keeps a