Critique of Anthropic merging user commands and agent skills
johnlindquist · x · 2026-09-01
Criticizes Anthropic for conflating user-invoked commands and agent-invoked skills. Argues commands shouldn't be in context (allow unlimited installs) and skills shouldn't be invoked by users. Notes that omp allows disabling model invocation.
More from coding & agent
- 9 AI concepts for 2026 edge: From Agentic Loops to Inference Economics — SucceededMind · 2026-09-01
- Frontier models are superhuman in Bash — I deleted every other tool and nothing broke — _philschmid · 2026-09-01
- Workshop: Shipping LLM systems that survive production — camerongreen95 · 2026-09-01
- Minimax H3 Fail: Forgot to link reference video, ruined environment — Thorozar · 2026-09-01
- Skip Frameworks, Build a Minimal Agent Loop First — omarsar0 · 2026-09-01
- Builder creates Pattern MCP to fix AI agent's poor UI design decisions — DonR954 · 2026-09-01