Skip to content

Skill · job · coding-agent

Coding agent

Ship a coding agent: AGENTS.md, apply_patch, repo map, tests in the loop, allow/ask/deny, human gate. Use for PR agents, SWE-bench-like work, repo edits, or when comparing Codex, OpenHands, Cline, Aider, Goose, Deep Agents. Start from a harness, not a blank graph.

GET /api/canon/skills/coding-agent?format=md

Every serious coding agent converges: workspace, skills, plan/act, diffs, sandbox, verifier, human gate. Computer-use is not the first tool.

When

The product is software engineering — PRs, tests, and a desk, not a chat wrapper.

Do

  1. 01

    Start from a harness

    Codex, OpenHands, Cline, Aider, Goose, Deep Agents. Replace pieces. Do not rebuild Claude Code poorly.

  2. 02

    Edit format + repo map

    apply_patch, not whole-file dumps. A map for orientation. Grep over read-whole-repo.

  3. 03

    Verify in the loop

    AGENTS.md test/typecheck/build as tools. Compact failures. Done is a reviewable PR + tests + human gate.

  4. 04

    Gate writes

    Plan mode denies writes. Act asks. Host prod creds never enter the sandbox.

Don't

  • Unsandboxed exec on the laptop with prod AWS.
  • Declare victory because the model said 'done'.
  • Screenshot the IDE instead of using git and tests.

Hard rules

  • Done = reviewable diff + tests + human gate.
  • No verifier in the loop is a block.
  • Skills for depth; AGENTS.md for commands and boundaries.

Refuse

  • Unsandboxed execA shell or code-act tool on the host with production credentials.
  • No verifier in the loopThe agent writes code and declares victory. Tests, typecheck, and build are optional.
  • Unbounded loopNo max-turns, token, wall-clock, or money budget. The agent rambles until the bill or the context dies.
  • Mega-toolOne function whose argument is a JSON blob of 'whatever'. An untyped shell with extra steps.
  • Computer-use as the first toolA browser or desktop agent used where an API, a workflow, or a grep would do.

Load with this

Load next

Trigger tests

Should fire

  • Build a coding agent that opens PRs
  • We want something like Cursor/Codex on our repo
  • The agent writes code but never runs tests

Should not

  • A support bot for refunds
  • Chat with our PDFs