A Practical Agentic Workflow Setup
tdhopper · x · 2026-07-12
This repost outlines the author's agentic setup, which fundamentally treats agents as routable and maintainable workflow systems:
- Using AGENTS.md as a router to guide agents to the right skills, docs, and tools.
- Preparing a standard workflow doc/skill tailored to personal needs, imported into the session via @/AGENTWORKFLOW.md.
- Maintaining self-healing documentation for each system, requiring agents to update docs alongside system changes. Summaries must be kept within the first 7 lines of each doc for easy retrieval, with this rule enforced in AGENTS.md.
- Having agents run and test the app themselves instead of relying solely on static reasoning.
Overall, it summarizes how to use agents more robustly and engineer them better, avoiding common pitfalls like missing context and outdated documentation.
More from coding & agent
- Cursor doubles usage limits across all plans for Grok, Composer and new models — XFreeze · 2026-07-22
- OpenWiki adds Gemini AI Studio and Enterprise Vertex AI support — BraceSproul · 2026-07-22
- Video-based proof of work is emerging as a feedback layer for coding agents — Vjeux · 2026-07-22
- Salesforce open-sources MCP+ to filter tool output before it reaches agents — msrivastav13 · 2026-07-22
- Anaconda acquires Kilo Code to expand into agentic software development — anacondainc · 2026-07-22
- Poolside’s laguna s 2.1 claims 118B MoE, 1M context, and 78.5% on SWE-bench Multilingual — ben_burtenshaw · 2026-07-22