Stacks

Somebody’s working setup, with the reasoning attached and a name on it. A set is things that go together. A flow is the same picking read in order: this is how I work on a monolith, and here is what I run at each point. The picking is the author’s. The numbers on each item are read off its repository and look the same wherever that item turns up, including inside somebody else’s stack.

• Write the thing that does not exist yet

  For the point where the answer stops being "install something" and starts being "build it". Two Anthropic meta-skills that make the skill-or-server decision legible, and the third-party one that tests the failure both of them leave open.

  1. 1Skill creator
  2. 2Mcp builder
  3. 3Mcp tester

  agentscli3 steps

• Write against the API that exists today

  The worst failure in third-party integration work does not look like a failure. The call is idiomatic, the types line up, and the method was removed two majors ago. Two items for what is true now, two for proving it stays true.

  • Context7
  • GitHub
  • Mockserver
  • Keploy

  agentscli4 items

• Read a codebase you did not write

  Four servers that answer the four different questions an agent gets wrong on a repository it has never seen: where is anything, why is it like that, what version am I calling, and what shape is the whole thing.

  • Serena MCP: the IDE for your agent
  • GitHub
  • Context7
  • Hustcc mcp mermaid

  agentscli4 items

• Find the cause before writing the fix

  A stack trace tells you where the program died, not where it went wrong. Five items that supply four different kinds of evidence, in the order an investigation actually needs them, and a test at the end that can say no.

  1. 1Root cause analysis
  2. 2Sentry mcp
  3. 3Serena MCP: the IDE for your agent
  4. 4GitHub
  5. and 1 more

  agentscli5 steps

• Change a schema without taking the site down

  The dangerous migration is not the one that fails. It is the one that runs perfectly and holds a lock on your busiest table for four minutes. One item for the idioms, one that reads the live schema, and two that read the SQL before anything does.

  1. 1Pg aiguide
  2. 2DBHub
  3. 3Migrationpilot
  4. 4Sqlsure

  agentscli4 steps

• Build the design, then go and look

  An agent implementing a design generates pixels and reasons in text. It will tell you the header is blue and centred while it renders red and left. Four items that make it read exact values, wait for the page to settle, actually look, and then keep looking after you have gone.

  1. 1Figma Context MCP
  2. 2Webapp testing
  3. 3Chrome DevTools MCP
  4. 4Playwright mcp

  agentscli4 steps

• A review that is not a rubber stamp

  Three systems that can each contradict the pull request description in a different way, and one procedure that makes the agent go and ask them. Reach without judgment is "LGTM, consider adding tests" in a costume.

  1. 1GitHub
  2. 2Context7
  3. 3Sentry mcp
  4. 4Open code review

  agentscli4 steps