Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
TypeScript agentic-aiai-agentsai-codinganthropicautomationclaudeclaude-codecodexcoding-agentsdevops-automationdevtoolsgithub-actionsgrokllmloop-engineeringmcpprompt-engineering
chore(loop): daily triage update STATE.md + run log [automated] (#655)
github-actions[bot]4bbde005d809
diff --git a/STATE.md b/STATE.mdindex 455c41e..767fe6a 100644--- a/STATE.md+++ b/STATE.md@@ -1,28 +1,29 @@# Loop State — loop-engineering reference-Last run: 2026-10-01T08:00:41Z (automated daily-triage workflow)+Last run: 2026-10-02T08:00:41Z (automated daily-triage workflow)## High Priority (loop is acting or waiting on human)- **2** dogfood workflow(s) failing — investigate `validate-patterns` / `audit`.-- [#567](https://github.com/cobusgreyling/loop-engineering/issues/567) **unanswered** 32d — AI Skill Shield scan report: cobusgreyling/loop-engineering (41 skills)+- [#567](https://github.com/cobusgreyling/loop-engineering/issues/567) **unanswered** 33d — AI Skill Shield scan report: cobusgreyling/loop-engineering (41 skills)## Watch List+- [#653](https://github.com/cobusgreyling/loop-engineering/pull/653) UNKNOWN — feat(loop-init): add cheaperinference model provider- [#648](https://github.com/cobusgreyling/loop-engineering/pull/648) UNKNOWN — chore(mcp): bump @modelcontextprotocol/sdk from 1.30.0 to 1.30.1 in /tools/mcp-server- [#647](https://github.com/cobusgreyling/loop-engineering/pull/647) UNKNOWN — chore(loop-init): bump @types/node from 26.6.2 to 26.6.3 in /tools/loop-init- [#645](https://github.com/cobusgreyling/loop-engineering/pull/645) UNKNOWN — chore(mcp): bump ip-address from 10.4.0 to 10.7.2 in /tools/mcp-server-- [#643](https://github.com/cobusgreyling/loop-engineering/pull/643) UNKNOWN — fix(loop-context): refuse a similarity threshold that switches stagnation off-- [#642](https://github.com/cobusgreyling/loop-engineering/pull/642) UNKNOWN — feat(loop-audit): score what is proven, not what is present-- [#641](https://github.com/cobusgreyling/loop-engineering/pull/641) UNKNOWN — fix: guard loops against prompt injection from untrusted input-- [#631](https://github.com/cobusgreyling/loop-engineering/pull/631) UNKNOWN — Sources: add the harness prompts a loop actually runs on top of-- [#622](https://github.com/cobusgreyling/loop-engineering/pull/622) UNKNOWN — Add loop-jev (TypeSafe System One) for cheaper loop decisions-- [#522](https://github.com/cobusgreyling/loop-engineering/issues/522) idle 33d — 如果我有一个项目需要重构,loop-engineering 怎么帮助我,来分解todo,然后自动进行,以下流程如何改造,有没有教程?-- [#508](https://github.com/cobusgreyling/loop-engineering/issues/508) idle 44d — Possible complementary direction: LongHorizon-Harness for sustained agent tasks-- [#486](https://github.com/cobusgreyling/loop-engineering/issues/486) idle 39d — Area owner invite: @AIMindCrafter for docs / examples / stories+- [#643](https://github.com/cobusgreyling/loop-engineering/pull/643) CI green, waiting on review/merge — fix(loop-context): refuse a similarity threshold that switches stagnation off+- [#642](https://github.com/cobusgreyling/loop-engineering/pull/642) CI green, waiting on review/merge — feat(loop-audit): score what is proven, not what is present+- [#641](https://github.com/cobusgreyling/loop-engineering/pull/641) CI green, waiting on review/merge — fix: guard loops against prompt injection from untrusted input+- [#631](https://github.com/cobusgreyling/loop-engineering/pull/631) CI green, waiting on review/merge — Sources: add the harness prompts a loop actually runs on top of+- [#622](https://github.com/cobusgreyling/loop-engineering/pull/622) CI green, waiting on review/merge — Add loop-jev (TypeSafe System One) for cheaper loop decisions+- [#522](https://github.com/cobusgreyling/loop-engineering/issues/522) idle 34d — 如果我有一个项目需要重构,loop-engineering 怎么帮助我,来分解todo,然后自动进行,以下流程如何改造,有没有教程?+- [#508](https://github.com/cobusgreyling/loop-engineering/issues/508) idle 45d — Possible complementary direction: LongHorizon-Harness for sustained agent tasks+- [#486](https://github.com/cobusgreyling/loop-engineering/issues/486) idle 40d — Area owner invite: @AIMindCrafter for docs / examples / stories- [#403](https://github.com/cobusgreyling/loop-engineering/issues/403) loop-report — Loop report — week of 2026-07-27-- [#262](https://github.com/cobusgreyling/loop-engineering/issues/262) idle 69d — Adopter: Pluribus — market/adoption research loop-- [#246](https://github.com/cobusgreyling/loop-engineering/issues/246) idle 82d — Resource suggestion: loop.js — a loop-engineering runtime where an independent Verify agent defines done+- [#262](https://github.com/cobusgreyling/loop-engineering/issues/262) idle 70d — Adopter: Pluribus — market/adoption research loop+- [#246](https://github.com/cobusgreyling/loop-engineering/issues/246) idle 83d — Resource suggestion: loop.js — a loop-engineering runtime where an independent Verify agent defines done- Loop Ready **100** (L3) — informational, not a reason to act.diff --git a/docs/last-run.json b/docs/last-run.jsonindex 59f0830..6b0b258 100644--- a/docs/last-run.json+++ b/docs/last-run.json@@ -1,6 +1,6 @@{"schemaVersion": 1,"label": "last triage",- "message": "2026-10-01",+ "message": "2026-10-02","color": "3ee8c5"}diff --git a/loop-run-log.md b/loop-run-log.mdindex d8454b7..8c7b528 100644--- a/loop-run-log.md+++ b/loop-run-log.md@@ -21,7 +21,6 @@ Append one entry per run. Prune entries older than 30 days.<!-- Loop appends below this line -->-{"run_id":"2026-09-02T08:00:41Z","pattern":"daily-triage","duration_s":8,"items_found":9,"actions_taken":1,"escalations":2,"tokens_estimate":52000,"readiness_score":100,"outcome":"escalated","workflow_run":"33606428461"}{"run_id":"2026-09-03T08:00:46Z","pattern":"daily-triage","duration_s":11,"items_found":9,"actions_taken":1,"escalations":0,"tokens_estimate":52000,"readiness_score":100,"outcome":"report-only","workflow_run":"33731028165"}{"run_id":"2026-09-04T08:03:05Z","pattern":"daily-triage","duration_s":158,"items_found":8,"actions_taken":1,"escalations":1,"tokens_estimate":52000,"readiness_score":100,"outcome":"report-only","workflow_run":"33851327595"}{"run_id":"2026-09-07T08:00:46Z","pattern":"daily-triage","duration_s":11,"items_found":9,"actions_taken":1,"escalations":4,"tokens_estimate":52000,"readiness_score":100,"outcome":"escalated","workflow_run":"34098301292"}@@ -43,3 +42,4 @@ Append one entry per run. Prune entries older than 30 days.{"run_id":"2026-09-29T08:00:49Z","pattern":"daily-triage","duration_s":8,"items_found":13,"actions_taken":1,"escalations":1,"tokens_estimate":52000,"readiness_score":100,"outcome":"report-only","workflow_run":"36540047730"}{"run_id":"2026-09-30T08:00:56Z","pattern":"daily-triage","duration_s":19,"items_found":17,"actions_taken":1,"escalations":3,"tokens_estimate":52000,"readiness_score":100,"outcome":"escalated","workflow_run":"36687040768"}{"run_id":"2026-10-01T08:00:41Z","pattern":"daily-triage","duration_s":8,"items_found":17,"actions_taken":1,"escalations":3,"tokens_estimate":52000,"readiness_score":100,"outcome":"escalated","workflow_run":"36833681714"}+{"run_id":"2026-10-02T08:00:41Z","pattern":"daily-triage","duration_s":10,"items_found":18,"actions_taken":1,"escalations":3,"tokens_estimate":52000,"readiness_score":100,"outcome":"escalated","workflow_run":"36981595435"}