Skip to content

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.

fix(ci): resolve validate-patterns errors and deprecation warnings

Cobus Greyling9265b52afe37
diff --git a/.github/workflows/audit.yml b/.github/workflows/audit.yml
index 89a22f0..4671987 100644
--- a/.github/workflows/audit.yml
+++ b/.github/workflows/audit.yml
@@ -17,11 +17,11 @@ jobs:
audit:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- - uses: actions/setup-node@v4
+ - uses: actions/setup-node@v6
with:
- node-version: '20'
+ node-version: '22'
cache: 'npm'
cache-dependency-path: tools/loop-audit/package-lock.json
@@ -61,7 +61,7 @@ jobs:
- name: Comment PR with loop readiness score
if: github.event_name == 'pull_request'
- uses: actions/github-script@v7
+ uses: actions/github-script@v9
with:
script: |
const fs = require('fs');
diff --git a/.github/workflows/daily-triage.yml b/.github/workflows/daily-triage.yml
index 379a116..c1198d6 100644
--- a/.github/workflows/daily-triage.yml
+++ b/.github/workflows/daily-triage.yml
@@ -13,11 +13,11 @@ jobs:
triage:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- - uses: actions/setup-node@v4
+ - uses: actions/setup-node@v6
with:
- node-version: '20'
+ node-version: '22'
cache: 'npm'
cache-dependency-path: tools/loop-audit/package-lock.json
diff --git a/.github/workflows/release-loop-audit.yml b/.github/workflows/release-loop-audit.yml
index 39d35ea..d4e72b4 100644
--- a/.github/workflows/release-loop-audit.yml
+++ b/.github/workflows/release-loop-audit.yml
@@ -13,11 +13,11 @@ jobs:
test-and-publish:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- - uses: actions/setup-node@v4
+ - uses: actions/setup-node@v6
with:
- node-version: '20'
+ node-version: '22'
registry-url: 'https://registry.npmjs.org'
cache: 'npm'
cache-dependency-path: tools/loop-audit/package-lock.json
diff --git a/.github/workflows/release-loop-init.yml b/.github/workflows/release-loop-init.yml
index 1d6bc9c..74e764f 100644
--- a/.github/workflows/release-loop-init.yml
+++ b/.github/workflows/release-loop-init.yml
@@ -13,11 +13,11 @@ jobs:
publish:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- - uses: actions/setup-node@v4
+ - uses: actions/setup-node@v6
with:
- node-version: '20'
+ node-version: '22'
registry-url: 'https://registry.npmjs.org'
- name: Build & publish
diff --git a/.github/workflows/validate-patterns.yml b/.github/workflows/validate-patterns.yml
index 2f6c83e..13c0875 100644
--- a/.github/workflows/validate-patterns.yml
+++ b/.github/workflows/validate-patterns.yml
@@ -10,7 +10,7 @@ jobs:
validate:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- name: Check registry covers all pattern files
run: |
@@ -26,12 +26,13 @@ jobs:
- name: Verify CONTRIBUTING + template compliance (basic)
run: |
+ set -e
echo "Checking that key sections exist in patterns (lightweight)"
for f in patterns/*.md; do
if [[ "$f" == *"README.md" ]]; then continue; fi
- grep -q "^## Scheduling" "$f" || (echo "Missing Scheduling in $f"; exit 1)
- grep -q "^## Required Skills" "$f" || (echo "Missing Required Skills in $f"; exit 1)
- grep -q "maker.*checker\|verifier\|Maker / Checker" "$f" || (echo "Missing verifier strategy in $f"; exit 1)
+ grep -q "^## Scheduling" "$f" || { echo "Missing Scheduling in $f"; exit 1; }
+ grep -q "^## Required Skills" "$f" || { echo "Missing Required Skills in $f"; exit 1; }
+ grep -Eq "maker.*checker|verifier|Maker / Checker|Verification Strategy|reviewer sub-agent" "$f" || { echo "Missing verifier strategy (maker/checker) mention in $f"; exit 1; }
done
echo "Basic pattern structure checks passed ✓"
diff --git a/examples/github-actions/ci-sweeper.yml b/examples/github-actions/ci-sweeper.yml
index bce0382..d06b2dd 100644
--- a/examples/github-actions/ci-sweeper.yml
+++ b/examples/github-actions/ci-sweeper.yml
@@ -18,7 +18,7 @@ jobs:
if: ${{ github.event.workflow_run.conclusion == 'failure' }}
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- name: Record failure context
run: |
diff --git a/examples/github-actions/daily-triage.yml b/examples/github-actions/daily-triage.yml
index 3dc46f9..1300b03 100644
--- a/examples/github-actions/daily-triage.yml
+++ b/examples/github-actions/daily-triage.yml
@@ -19,7 +19,7 @@ jobs:
triage:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
- name: Gather CI context
id: ci
diff --git a/examples/github-actions/post-merge-cleanup.yml b/examples/github-actions/post-merge-cleanup.yml
index e38fd38..72a6653 100644
--- a/examples/github-actions/post-merge-cleanup.yml
+++ b/examples/github-actions/post-merge-cleanup.yml
@@ -16,7 +16,7 @@ jobs:
cleanup-scan:
runs-on: ubuntu-latest
steps:
- - uses: actions/checkout@v4
+ - uses: actions/checkout@v6
with:
fetch-depth: 50
diff --git a/patterns/daily-triage.md b/patterns/daily-triage.md
index 87f5b5b..d7636fb 100644
--- a/patterns/daily-triage.md
+++ b/patterns/daily-triage.md
@@ -68,7 +68,7 @@ Fields the loop must update every run:
**Grok Build TUI**:
```bash
-/loop 1d Run the loop-triage skill. Append high-priority items to STATE.md. For obvious small bugfixes only: worktree + minimal-fix + reviewer sub-agent. Flag ambiguous items for human review.
+/loop 1d Run the loop-triage skill. Append high-priority items to STATE.md. For obvious small bugfixes only: worktree + minimal-fix + verifier sub-agent (maker/checker). Flag ambiguous items for human review.
```
**Claude Code**:
diff --git a/patterns/pr-babysitter.md b/patterns/pr-babysitter.md
index 6d987a6..33c07bd 100644
--- a/patterns/pr-babysitter.md
+++ b/patterns/pr-babysitter.md
@@ -47,7 +47,7 @@ Example state entry:
## Verification Strategy
- Never let the implementer sub-agent mark its own work "done".
-- Use a separate reviewer sub-agent (or a stronger model on higher effort) that must explicitly confirm:
+- Use a separate verifier sub-agent (maker/checker) (or a stronger model on higher effort) that must explicitly confirm:
- The change addresses the comment/failure.
- No unrelated files were touched.
- Tests/lint still pass in the worktree.
@@ -78,7 +78,7 @@ Example state entry:
## Failure Modes & Mitigations
-- **Loop proposes bad fixes** → Strong reviewer sub-agent + human review gate for anything beyond trivial.
+- **Loop proposes bad fixes** → Strong verifier sub-agent (maker/checker) + human review gate for anything beyond trivial.
- **Infinite rebase loops** → Limit number of automated rebase attempts per PR.
- **Stale state** → The loop should prune closed/merged PRs on every run.
- **Notification fatigue** → Use selective notifications (only when human action is truly required).