Files
Daniel Avila 7f890b1b3b feat: add Loops component type with referenced components (#643)
* feat: add Loops component type with referenced components

Introduce "loops" as a new first-class component type — autonomous
agentic workflows (goal + interval + stop condition) inspired by Loop
Engineering and the Forward Future Loop Library. A loop references other
components (agents, skills, hooks, commands) and the dashboard renders
those references as clickable cards on the loop detail page.

- Add 10 starter loops under cli-tool/components/loops/
  (engineering, evaluation, operations)
- Catalog generator: scan loops + write per-component content files
- Dashboard: new type in icons/types/data, /loops page, and a
  "Referenced Components" section on the loop detail page
- CLI: --loop flag installs the loop to .claude/loops/ and
  auto-installs its referenced components
- Docs: CLAUDE.md and cli-tool rule updated

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES

* feat: add 8 more loops (goal/loop/schedule patterns)

Expand the loops catalog to 18, drawing ideas from community "Loop
Engineering" patterns. Adds loops across the three trigger verbs
(/goal, /loop, /schedule) and emphasizes the verifier-in-the-loop and
budget / anti-spin guardrails:

- engineering/five-minute-maintainer-loop
- engineering/build-test-fix-loop
- engineering/anti-spin-build-loop
- engineering/completion-contract-loop (goal)
- engineering/goal-refiner-loop (goal)
- engineering/adversarial-review-loop (cross-model)
- operations/overnight-pr-routine-loop (schedule)
- evaluation/human-approval-loop (human-in-the-loop)

All referenced components verified to exist; catalog regenerated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-06-21 20:19:16 -04:00

1 line
2.3 KiB
JSON

{"content": "---\nname: devils-advocate-loop\ndescription: Adversarially challenges a design or decision until every serious objection is resolved or explicitly accepted.\ncategory: evaluation\ninterval: 15m\nstop-condition: No unresolved serious objections remain — each is fixed or consciously accepted with rationale.\ncomponents: [agent:expert-advisors/architect-review, agent:expert-advisors/critical-thinking, command:git-workflow/pr-review]\ntags: [evaluation, design-review, decision-making, loop]\n---\n\n# Devil's-Advocate Loop\n\n> **Loop Engineering** — put a dedicated critic in the loop. It keeps attacking the design until the proposal survives scrutiny or is knowingly accepted with its trade-offs.\n\n## 🎯 Goal\nStress-test a design, RFC, or architectural decision by generating the strongest possible objections, then resolving or explicitly accepting each one — no objection silently ignored.\n\n## ⏱️ Schedule\nSuggested interval: `15m` (or run until the design is settled).\n\n## ▶️ Run it\n```\n/loop 15m \"Act as a devil's advocate against the current design. Raise the strongest objections (scaling, security, cost, edge cases, maintainability). For each, either fix the design or record an explicit accepted trade-off with rationale. Continue until no serious objection is unresolved.\"\n```\n\n## 🔁 Iteration steps\n1. **Perceive** — read the current design/decision.\n2. **Reason** — the `critical-thinking` agent generates the strongest counter-arguments.\n3. **Plan** — for each objection, choose fix vs accept-with-rationale.\n4. **Act** — update the design or the decision log; `architect-review` validates the revision.\n5. **Observe** — re-run with `/pr-review`; stop only when nothing serious is unresolved.\n\n## 🛑 Stopping condition\nEvery serious objection is either resolved or recorded as an explicit, justified trade-off.\n\n## 🧩 Referenced components\n- `agent:expert-advisors/architect-review` — validates each revision.\n- `agent:expert-advisors/critical-thinking` — generates adversarial objections.\n- `command:git-workflow/pr-review` — structured review of the design changes.\n\n## 💡 Example\nA proposed single-region database is challenged on availability; the loop either adds a replication plan or records \"single-region accepted for MVP, revisit at scale\" with reasoning.\n"}