The Node content pipeline (agents/) and the astroagent in-site authoring
console are a proprietary, CLI-strategy agent system that shouldn't ship in
the cloneable SeedProject base. Remove both and all their wiring:
- Delete agents/ (pipeline scripts, prompts, admin server, libs) + runtime
- Delete astroagent config, app/.astroagent/ skill, DevConsole component;
unhook it from BaseLayout.astro and astro.config.mjs preview env logic
- Delete api/cli/resources.php (DB->pipeline resource bridge)
- Drop agent blocks from configure.mjs, agent runtime rules from .gitignore,
topic/audience from site.config.json, agent prompts from new-site.sh
- Strip agent sections from AGENTS.md / README.md / api/.memory/foundation.md
Kept: api/app/LLM/* (API-key/REST multi-provider layer — distinct from the
CLI agents), api/cli/rebuild.php, and the mde_resources schema.
Frontend build verified (npm run build → 14 pages).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DfzaSFv5okUxCCdvq5RXu1
Adopt the agents/ architecture proven on medellin.co (reference impl):
- Move the content engine to a top-level agents/ dir: orchestrators, prompts,
config, run.sh, admin console, shared libs. All content-pipeline literals
repointed (config paths, scripts, admin, LLM-facing prompts/image.md string,
configure.mjs, new-site.sh, astroagent tokenFile, .gitignore runtime block).
- Every script carries a parseable @agent-manifest header: name, title, class
(content|operational|runtime|plumbing), trigger, model, prompts, skills (MCP),
tools, reads/writes tables. 5 content agents + 3 plumbing scripts.
- New agents/catalog.mjs generates the catalog from the headers:
agents/AGENTS.md (human, grouped by class) + agents/agents.json (machine
manifest — a clone diffs it against a source to find missing tools/tables/MCP
before running). configure.mjs regenerates the catalog on every identity
stamp. No DB table, no watcher.
- config.json gains paths.stateDir/newsDir; publish-tick, write-daily, and
news-radar read them instead of hardcoding.
- Full cut: content-pipeline/ deleted (the seed has no live crons, so no
hybrid period needed). Docs updated (AGENTS.md structure + pipeline section,
README paths).
Clones migrating from content-pipeline/: see medellin.co's
.memory/handoffs/agents-directory-migration.md for the cutover playbook
(one cron set active at a time; migrate drafts/state after repointing cron).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FMQeUnUrAeexcZ7P2Hxa6G
- AGENTS.md / CLAUDE.md: tell any agent (Claude Code, astroagent, Codex) what the
base is and the exact fresh-clone setup flow (new-site.sh / configure.mjs / build)
- configure.mjs: stamp astroagent ai.agentUser as <slug>-agent (was stale 'comiida-agent')
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SYHWLHihq3v9nxNwoPCKSn
- site.config.json single source of identity (name/url/description/author/social)
- scripts/configure.mjs stamps it into app, content-pipeline, and astroagent configs
- app/src/lib/blog-data.js SITE + author now read from app/src/config/site.json
- astro.config.mjs default site URL from config
- index.astro / Footer.astro neutralized hardcoded title, hero alt, social link
- sample 'welcome' post + placeholder hero/avatar so the site builds out of the box
Verified: cd app && npm ci && npm run build -> 13 pages, Complete.
Remaining comiida demo prose in about/faq/services/contact + Newsletter (sample content).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SYHWLHihq3v9nxNwoPCKSn
