Daniel Avila
7f890b1b3b
* 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>
2.7 KiB
name, description, category, interval, stop-condition, components, tags
| name | description | category | interval | stop-condition | components | tags | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| completion-contract-loop | Writes a contract of what "done" means and what evidence proves each requirement before any work starts, then refuses to claim success without that evidence. | engineering | on-demand | Every requirement in the completion contract is satisfied with verifiable evidence (tests, output, diffs). |
|
|
Completion-Contract Loop
Loop Engineering — the
/goalverb runs until a verifiable condition is true. This loop fixes the most common failure: an agent that says "done" when it isn't. It defines "complete" and the evidence for each requirement upfront, then can't declare victory without it.
🎯 Goal
Before doing any work, write a completion contract: each requirement plus the concrete evidence that proves it. Then execute until every requirement is backed by evidence.
⏱️ Schedule
Trigger: on-demand (a goal that runs to a condition, not a timer).
▶️ Run it
/goal First write a completion contract: list each requirement and the exact evidence that proves it (a passing test, a command output, a diff). Confirm the contract, then implement. Do not claim success for any requirement without its evidence. Done only when every requirement has evidence. Stop after N turns if blocked.
🔁 Iteration steps
- Contract —
critical-thinkingdrafts requirements + the evidence each needs. - Plan — order the work by requirement.
- Act — implement one requirement at a time.
- Prove — attach evidence (coverage via
/test-coverage, command output, diff); no evidence, not done. - Observe — when all requirements have evidence, open a PR with
/create-prlinking the contract.
🛑 Stopping condition
Every contract requirement is satisfied with verifiable evidence — or the turn/budget cap is hit and the loop reports what's still unproven.
💰 Budget & guardrails
A separate check confirms each piece of evidence rather than trusting the worker's self-report. Hard turn cap so an unprovable requirement can't spin.
🧩 Referenced components
agent:expert-advisors/critical-thinking— authors and enforces the contract.command:testing/test-coverage— supplies measurable evidence.command:git-workflow/create-pr— ships the result with the contract attached.
💡 Example
Asked to "add rate limiting", the loop first writes a contract (limit enforced, 429 returned, headers set, tested) and only reports done once each line has a passing test as evidence.