Make it automatic

MCP gives an agent tools; a skill gives it behavior. Install the ctxfile behavior pack once and any agent, while doing its normal work, knows when to checkpoint context and how to do it well. You stop prompting “save this”; when you switch providers, the data is simply already there. Prompting remains as a manual override.

Install

ctxfile init

init asks for consent first (auto-capture is an explicit choice, never a default you discover later), then detects your harnesses and installs the behavior file where each one looks:

HarnessWhat init writesManual alternative
Claude Code.claude/skills/ctxfile/SKILL.mdctxfile init --print claude-code
Cursor.cursor/rules/ctxfile.mdc (always applied)ctxfile init --print cursor
AGENTS.md harnessesA managed block appended to AGENTS.md (re-install updates it in place)ctxfile init --print agents-md
CodexPrinted for pasting into your Codex instructionsctxfile init --print codex
Anything elseA generic system-prompt block for any harness or open modelctxfile init --print generic

All five renders come from one canonical spec in the package (behaviors/canonical.md); community PRs for new harnesses are markdown, the same cheap-connector dynamic as the ingest prompt snippets.

What the skill teaches the agent

The guardrails (server-enforced, not just requested)

Automatic checkpoints carry trigger: "auto" provenance, and the server holds the line even if an agent misbehaves:

A silent ambient recorder would contradict the entire trust story; a narrated one reinforces it. That is why the announcement line is a behavior rule AND baked into the tool's response text.

Try the loop

ctxfile init --yes
# work in Claude Code / Cursor as normal; when a task completes you'll see:
#   ✓ Checkpointed to ctxfile (thread: <your work>)
ctxfile threads          # it's there
ctxfile pause            # and now it isn't captured, until:
ctxfile resume