linkedin-studio/hooks/scripts/pre-compact.mjs
Kjell Tore Guttormsen 40986575b6 feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 08:58:35 +02:00

29 lines
864 B
JavaScript

#!/usr/bin/env node
// pre-compact.mjs
// PreCompact hook for linkedin-thought-leadership plugin
// Reminds Claude to preserve critical LinkedIn session context before compaction
//
// Exit codes:
// 0 - Always allow (informational hook)
const context = [
'Before compacting context, preserve these critical LinkedIn session details:',
'- Current post draft (full text if in progress)',
'- Chosen angle and format',
'- User feedback and iteration direction',
'- Quality check results',
'- State file values (streak, weekly count, last post date)',
'- Any planned topics or next steps',
'Ensure these survive the context compaction.',
].join('\n');
const output = {
continue: true,
hookSpecificOutput: {
hookEventName: 'PreCompact',
additionalContext: context,
},
};
process.stdout.write(JSON.stringify(output));
process.exit(0);