Skip to content
← Public packages

@kentcdodds/closing-the-agentic-loop

Closing the Agentic Loop: Kent C. Dodds's talk and workshop deck. Default short talk; ?event=aie-2026 is the AIE hour cut with a Podium QR; ?format=full adds labs.

FollowForkOpen app

Files

rungs.json

110 lines · 4.9 KB · JSON
{
  "_readme": "Rung wording and grouping are copied verbatim from the autopilot SKILL.md that kcd-skills 1.5.0 prints (npx kcd-skills@latest autopilot; latest on npm as of Nov 1 2026, package gitHead 5544656). Backticks render as code. Edit this file when the skill changes, then run `npm run build`. Scores are done | partial | missing | unknown | n/a, or null when the mediarss dry run has no score for that rung; set showScores false if they no longer line up with the rungs.",
  "skillVersion": "kcd-skills 1.5.0",
  "scoreSource": "mediarss dry run (read-only audit), Oct 18 2026",
  "showScores": true,
  "groups": [
    {
      "id": "P1",
      "label": "Good PRs",
      "rungs": [
        {
          "n": 1,
          "title": "Agent map + verify",
          "doneWhen": "a short `AGENTS.md` (or equivalent) linking the docs agents use; one verify command (tests, typecheck where the language has one, lint, format) CI runs in full. Commit and pre-push hooks run the fast static checks (lint, format, typecheck, dead-code checks); CI time budgets fail only on real problems.",
          "score": "partial"
        },
        {
          "n": 2,
          "title": "Decisions directory",
          "doneWhen": "ADRs for multi-PR decisions and the \"no\", each with \"Revisit if\".",
          "score": "missing"
        },
        {
          "n": 3,
          "title": "Primitives catalog",
          "doneWhen": "building blocks, code roots, and an `adrs` list per entry (current records that shape it, `[]` when none), kept short. A PR that adds or reshapes a primitive, or writes or supersedes an ADR, updates the matching `adrs` lists in the same PR.",
          "score": "partial"
        },
        {
          "n": 4,
          "title": "Self-verification",
          "doneWhen": "agents run their change locally with a project control CLI (`doctor`, `dev`, `login`, `request --contains`, `execute`, `browse`, `health --sha`) and a `control-<project>` skill. For apps with routes, a Feature Map generated from the framework's route list, with seed-and-reach notes, checked in CI. Previews cover production-like checks. Model: Kody's `control-kody`; see `npx kcd-skills@latest autopilot verification`.",
          "score": "partial"
        },
        {
          "n": 5,
          "title": "PR template",
          "doneWhen": "Intent, Why, Door, Cleanup, Testing, System recap.",
          "score": "partial"
        }
      ]
    },
    {
      "id": "P2",
      "label": "Review and verification",
      "rungs": [
        {
          "n": 6,
          "title": "Ship loop",
          "doneWhen": "Kody `ship-pr` or `kcd-skills autopilot ship-pr` + config, behind a thin `ship-pr` skill.",
          "score": "partial"
        },
        {
          "n": 7,
          "title": "Reviewers + previews",
          "doneWhen": "AI reviewers per tier scrutinize test-expectation changes made with the code they test; previews for production-like changes; agent merge; running-version check after deploy. Reviewers check each PR against the project's principles (when it has them), and each principle a machine can check becomes a lint rule or test.",
          "score": "partial"
        }
      ]
    },
    {
      "id": "P3",
      "label": "Blast radius",
      "rungs": [
        {
          "n": 8,
          "title": "Flags + rollback",
          "doneWhen": "flags with owner, metric, removal condition; rollback runbook.",
          "score": "partial"
        },
        {
          "n": 9,
          "title": "Backups",
          "doneWhen": "scheduled, isolated restore test.",
          "score": "partial"
        }
      ]
    },
    {
      "id": "KI",
      "label": "Keep improving",
      "rungs": [
        {
          "n": 10,
          "title": "Friction form",
          "doneWhen": "issue form + `friction`, `friction-skipped` labels, filed by every ship loop and triaged (rung 11).",
          "score": "partial"
        },
        {
          "n": 11,
          "title": "Triage",
          "doneWhen": "every issue agents file (friction, cleanup, errors) gets a priority and, when it needs a human call, the project's decision marker. Agents work the highest priority first; decision-marked issues wait for the human's call. Default: `P0`-`P3` labels + `needs-decision`; the team's own scheme (labels, a project-board field, a tracker priority field) from the interview takes its place.",
          "score": null
        },
        {
          "n": 12,
          "title": "Cleanup issues",
          "doneWhen": "`Cleanup:` issues with a falsifiable \"ready when\", triaged (rung 11).",
          "score": "missing"
        },
        {
          "n": 13,
          "title": "Cleanup cron agents",
          "doneWhen": "(daily friction sweep, errors → issues, docs freshness and pruning, test pruning, weekly legacy reaper) open PRs, highest priority first (rung 11); only low/medium risk with green CI auto-merges. See templates → Cleanup automations.",
          "score": "missing"
        }
      ]
    }
  ]
}