@haus-tech/haus-workflow 6.7.1 → 6.8.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +12 -0
- package/dist/cli.js +4617 -1761
- package/package.json +3 -1
- package/packages/agents/issue-creator.md +61 -0
- package/packages/configs/eslint/eslint.config.mjs +90 -0
- package/packages/configs/lighthouse/lighthouserc.yml +35 -0
- package/packages/configs/prettier/.prettierignore +28 -0
- package/packages/configs/prettier/prettier.config.cjs +12 -0
- package/packages/packages.yaml +81 -0
- package/packages/skills/adr-decisions/SKILL.md +114 -0
- package/packages/skills/auth-oidc-azure-bankid-patterns/SKILL.md +46 -0
- package/packages/skills/auth-oidc-azure-bankid-patterns/references/conventions.md +29 -0
- package/packages/skills/auth-oidc-azure-bankid-patterns/references/scope.md +30 -0
- package/packages/skills/auth-oidc-azure-bankid-patterns/references/workflow.md +38 -0
- package/packages/skills/bullmq-patterns/SKILL.md +63 -0
- package/packages/skills/bullmq-patterns/references/conventions.md +33 -0
- package/packages/skills/bullmq-patterns/references/scope.md +30 -0
- package/packages/skills/bullmq-patterns/references/workflow.md +50 -0
- package/packages/skills/i18next-patterns/SKILL.md +62 -0
- package/packages/skills/i18next-patterns/references/conventions.md +32 -0
- package/packages/skills/i18next-patterns/references/scope.md +29 -0
- package/packages/skills/i18next-patterns/references/workflow.md +39 -0
- package/packages/skills/issue-authoring/SKILL.md +191 -0
- package/packages/skills/issue-authoring/references/issue-tracker.md +29 -0
- package/packages/skills/issue-authoring/references/native-metadata.md +122 -0
- package/packages/skills/issue-authoring/references/recording-approval.md +29 -0
- package/packages/skills/laravel-nova-patterns/SKILL.md +55 -0
- package/packages/skills/laravel-nova-patterns/references/conventions.md +26 -0
- package/packages/skills/laravel-nova-patterns/references/scope.md +30 -0
- package/packages/skills/laravel-nova-patterns/references/workflow.md +36 -0
- package/packages/skills/nextauth-patterns/SKILL.md +48 -0
- package/packages/skills/nextauth-patterns/references/conventions.md +33 -0
- package/packages/skills/nextauth-patterns/references/scope.md +33 -0
- package/packages/skills/nextauth-patterns/references/workflow.md +46 -0
- package/packages/skills/nx-tag-conventions/SKILL.md +32 -0
- package/packages/skills/package-manager-yarn4-pnpm89/SKILL.md +41 -0
- package/packages/skills/package-manager-yarn4-pnpm89/references/conventions.md +25 -0
- package/packages/skills/package-manager-yarn4-pnpm89/references/scope.md +30 -0
- package/packages/skills/package-manager-yarn4-pnpm89/references/workflow.md +39 -0
- package/packages/skills/qliro-patterns/SKILL.md +48 -0
- package/packages/skills/qliro-patterns/references/conventions.md +28 -0
- package/packages/skills/qliro-patterns/references/scope.md +30 -0
- package/packages/skills/qliro-patterns/references/workflow.md +46 -0
- package/packages/skills/react-router-v7-patterns/SKILL.md +47 -0
- package/packages/skills/react-router-v7-patterns/references/conventions.md +30 -0
- package/packages/skills/react-router-v7-patterns/references/scope.md +32 -0
- package/packages/skills/react-router-v7-patterns/references/workflow.md +43 -0
- package/{library/global → packages}/skills/request/scripts/korning.mjs +1 -1
- package/packages/skills/strapi-patterns/SKILL.md +63 -0
- package/packages/skills/strapi-patterns/references/conventions.md +33 -0
- package/packages/skills/strapi-patterns/references/scope.md +29 -0
- package/packages/skills/strapi-patterns/references/workflow.md +47 -0
- package/packages/skills/vendure-app-patterns/SKILL.md +44 -0
- package/packages/skills/vendure-app-patterns/references/conventions.md +25 -0
- package/packages/skills/vendure-app-patterns/references/scope.md +29 -0
- package/packages/skills/vendure-app-patterns/references/workflow.md +45 -0
- package/packages/skills/vendure-plugin-patterns/SKILL.md +55 -0
- package/packages/skills/vendure-plugin-patterns/references/conventions.md +27 -0
- package/packages/skills/vendure-plugin-patterns/references/scope.md +30 -0
- package/packages/skills/vendure-plugin-patterns/references/workflow.md +42 -0
- package/packages/skills/whats-installed/SKILL.md +53 -0
- package/packages/skills/wordpress-acf-elementor-jetengine-patterns/SKILL.md +41 -0
- package/packages/skills/wordpress-acf-elementor-jetengine-patterns/references/conventions.md +25 -0
- package/packages/skills/wordpress-acf-elementor-jetengine-patterns/references/scope.md +28 -0
- package/packages/skills/wordpress-acf-elementor-jetengine-patterns/references/workflow.md +41 -0
- package/packages/skills/wordpress-bedrock-patterns/SKILL.md +41 -0
- package/packages/skills/wordpress-bedrock-patterns/references/conventions.md +27 -0
- package/packages/skills/wordpress-bedrock-patterns/references/scope.md +28 -0
- package/packages/skills/wordpress-bedrock-patterns/references/workflow.md +42 -0
- package/packages/skills/writing-documentation/SKILL.md +161 -0
- package/packages/skills/writing-documentation/references/claude-template-workspace.md +60 -0
- package/packages/skills/writing-documentation/references/claude-template.md +43 -0
- package/packages/skills/writing-documentation/references/completeness-criteria.md +26 -0
- package/packages/skills/writing-documentation/references/summary-template.md +81 -0
- package/packages/skills/writing-documentation/references/topic-file-formats.md +125 -0
- package/packages/skills/writing-documentation/references/validation-checklist.md +42 -0
- package/packages/templates/agentic-workflow-poc.md +180 -0
- package/packages/templates/agentic-workflow-standard.md +160 -0
- package/packages/templates/decision-template.md +27 -0
- package/packages/templates/decisions-ci-gate.yml +32 -0
- package/packages/templates/lefthook-branch-guard.yml +27 -0
- package/packages/templates/lefthook-lighthouse.yml +28 -0
- package/packages/templates/lefthook-quality.yml +34 -0
- package/packages/templates/lefthook-security.yml +27 -0
- package/packages/templates/start-here.md +72 -0
- /package/{library/global → packages}/agents/request-assessor.md +0 -0
- /package/{library/global → packages}/agents/request-design-reviewer.md +0 -0
- /package/{library/global → packages}/agents/request-designer.md +0 -0
- /package/{library/global → packages}/agents/request-scorer.md +0 -0
- /package/{library/global → packages}/agents/request-specifier-eskalerad.md +0 -0
- /package/{library/global → packages}/agents/request-specifier.md +0 -0
- /package/{library/global → packages}/skills/haus-workflow/SKILL.md +0 -0
- /package/{library/global → packages}/skills/haus-workflow/references/clone.md +0 -0
- /package/{library/global → packages}/skills/haus-workflow/references/init.md +0 -0
- /package/{library/global → packages}/skills/haus-workflow/references/new.md +0 -0
- /package/{library/global → packages}/skills/request/SKILL.md +0 -0
- /package/{library/global → packages}/skills/request/scripts/archive.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/bedom.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/check-lasta.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/compare-scores.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/contract-check.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/kontroll.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/lib.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/precheck.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/ref-hash.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/report.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/resolve-anchors.mjs +0 -0
- /package/{library/global → packages}/skills/request/scripts/svep.mjs +0 -0
- /package/{library/global → packages}/skills/request-assess-impact/SKILL.md +0 -0
- /package/{library/global → packages}/skills/request-score/SKILL.md +0 -0
- /package/{library/global → packages}/skills/request-score/references/poangskala.md +0 -0
- /package/{library/global → packages}/skills/request-sync/SKILL.md +0 -0
- /package/{library/global → packages}/skills/request-write-spec/SKILL.md +0 -0
- /package/{library/global → packages}/skills/request-write-spec/references/specformat.md +0 -0
- /package/{library/global → packages}/skills/slack-cowork/SKILL.md +0 -0
- /package/{library/global → packages}/skills/slack-cowork/references/canvas-markdown.md +0 -0
- /package/{library/global → packages}/skills/slack-cowork/references/synk.md +0 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@haus-tech/haus-workflow",
|
|
3
|
-
"version": "6.
|
|
3
|
+
"version": "6.8.0",
|
|
4
4
|
"description": "Haus AI workflow CLI for Claude Code.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
|
@@ -15,6 +15,7 @@
|
|
|
15
15
|
"dist",
|
|
16
16
|
"scripts/postinstall.mjs",
|
|
17
17
|
"library/global",
|
|
18
|
+
"packages",
|
|
18
19
|
"library/catalog",
|
|
19
20
|
"library/schemas",
|
|
20
21
|
"README.md",
|
|
@@ -39,6 +40,7 @@
|
|
|
39
40
|
"release": "GITHUB_TOKEN=$(gh auth token) LEFTHOOK_EXCLUDE=branch-guard,ci-local release-it",
|
|
40
41
|
"release:dry": "GITHUB_TOKEN=$(gh auth token) LEFTHOOK_EXCLUDE=branch-guard,ci-local release-it --dry-run",
|
|
41
42
|
"prepack": "yarn build",
|
|
43
|
+
"check:packages": "node scripts/check-packages.mjs",
|
|
42
44
|
"verify": "node scripts/verify.mjs",
|
|
43
45
|
"verify:full": "node scripts/verify.mjs --coverage",
|
|
44
46
|
"ci:local": "node scripts/ci-local.mjs --force",
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: issue-creator
|
|
3
|
+
description: File GitHub issues for verified findings, deferred scope items,
|
|
4
|
+
or ideas, using the two-audience house format with native issue fields.
|
|
5
|
+
Use instead of creating background-task chips. Ideas only on explicit
|
|
6
|
+
human request.
|
|
7
|
+
model: sonnet
|
|
8
|
+
tools: Read, Grep, Glob, Bash, Write
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
Load the `issue-authoring` skill and follow it exactly. If that skill is not
|
|
12
|
+
installed or otherwise unavailable, abort and report that — the format,
|
|
13
|
+
approval header, and idea restriction all live in the skill; this agent has
|
|
14
|
+
no standalone format and cannot function without it.
|
|
15
|
+
|
|
16
|
+
Modes: `finding` | `deferred` | `idea`.
|
|
17
|
+
|
|
18
|
+
Before creating anything:
|
|
19
|
+
|
|
20
|
+
1. Route each item per the skill's Routing section: findings about
|
|
21
|
+
haus-shipped content (a skill, agent, rule, template, or the workflow
|
|
22
|
+
standard) file against `WeAreHausTech/haus-workflow-catalog`; findings about
|
|
23
|
+
the haus CLI itself (a command, a gate, a guard hook, a file the CLI
|
|
24
|
+
writes, or a skill or agent it ships itself) file against
|
|
25
|
+
`WeAreHausTech/haus-workflow`; everything else files locally. Then confirm
|
|
26
|
+
GitHub issues are available on that destination:
|
|
27
|
+
`gh repo view [<owner>/<repo>] --json nameWithOwner,hasIssuesEnabled`.
|
|
28
|
+
If this fails for the local repo or reports `hasIssuesEnabled: false`,
|
|
29
|
+
abort and report why — the caller creates a background-task chip instead.
|
|
30
|
+
If only the upstream repo is unreachable, fall back per the skill (file
|
|
31
|
+
locally with the routing marker) and report the fallback.
|
|
32
|
+
2. Detect native support: issue types enabled? Priority/Effort fields pinned?
|
|
33
|
+
The detection query, the capability query and the native-vs-fallback table
|
|
34
|
+
are in the skill's `references/native-metadata.md` — read it rather than
|
|
35
|
+
improvising a query, and fall back per that table if support is absent.
|
|
36
|
+
3. Verify every file:line claim against the current working tree — findings
|
|
37
|
+
go stale between sessions.
|
|
38
|
+
4. Run the dedupe search IMMEDIATELY before `gh issue create`, not earlier.
|
|
39
|
+
Search titles and bodies, in English and Swedish.
|
|
40
|
+
|
|
41
|
+
Write each issue body with the `Write` tool where possible. If you must fall
|
|
42
|
+
back to a Bash heredoc, it MUST be quoted — `cat > "$f" <<'EOF'` — never
|
|
43
|
+
unquoted: bodies quote repo code containing `$VAR`, `` ` ``, and `$(...)`,
|
|
44
|
+
and an unquoted heredoc expands or executes it.
|
|
45
|
+
|
|
46
|
+
`idea` mode is spawn-gated, not self-certified: the spawning prompt MUST
|
|
47
|
+
quote the human's own words asking for the idea to be recorded. If it does
|
|
48
|
+
not, refuse to file and report why instead.
|
|
49
|
+
|
|
50
|
+
After the batch: second pass for relationships (sub-issues, #n cross-refs).
|
|
51
|
+
Every auto-filed issue — `finding` or `deferred` — gets `needs-triage`; this
|
|
52
|
+
is not blanket permission to auto-file ideas, which stay gated on the rule
|
|
53
|
+
above.
|
|
54
|
+
|
|
55
|
+
YOU MUST NEVER implement, edit, or commit anything you file. Your `Bash` and
|
|
56
|
+
`Write` tools can edit files and commit, and nothing in the harness stops
|
|
57
|
+
you — this rule holds only because you hold it (ADR-0044). `Bash` is for `gh`
|
|
58
|
+
and read-only inspection; `Write` is for issue-body files. Filing is the whole
|
|
59
|
+
deliverable.
|
|
60
|
+
|
|
61
|
+
Report back: a table of issue URL · type · priority · effort · labels · relations.
|
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
import js from '@eslint/js'
|
|
2
|
+
import globals from 'globals'
|
|
3
|
+
import tseslint from 'typescript-eslint'
|
|
4
|
+
import pluginReact from 'eslint-plugin-react'
|
|
5
|
+
import pluginReactHooks from 'eslint-plugin-react-hooks'
|
|
6
|
+
import jsxA11y from 'eslint-plugin-jsx-a11y'
|
|
7
|
+
import { defineConfig } from 'eslint/config'
|
|
8
|
+
import eslintConfigPrettier from 'eslint-config-prettier/flat'
|
|
9
|
+
import pluginQuery from '@tanstack/eslint-plugin-query'
|
|
10
|
+
|
|
11
|
+
export default defineConfig([
|
|
12
|
+
// Ignore generated and build output
|
|
13
|
+
{
|
|
14
|
+
ignores: ['node_modules/**', 'build/**', 'dist/**', '.react-router/**'],
|
|
15
|
+
},
|
|
16
|
+
|
|
17
|
+
// Core JS recommended rules
|
|
18
|
+
js.configs.recommended,
|
|
19
|
+
|
|
20
|
+
// TypeScript recommended rules (flat configs array)
|
|
21
|
+
...tseslint.configs.recommended,
|
|
22
|
+
...tseslint.configs.strict,
|
|
23
|
+
|
|
24
|
+
// React recommended rules (flat configs array)
|
|
25
|
+
pluginReact.configs.flat.recommended,
|
|
26
|
+
|
|
27
|
+
// Tanstack Query recommended rules (flat configs array)
|
|
28
|
+
pluginQuery.configs['flat/recommended'],
|
|
29
|
+
|
|
30
|
+
// JSX A11y recommended rules (flat configs array)
|
|
31
|
+
jsxA11y.flatConfigs.recommended,
|
|
32
|
+
|
|
33
|
+
// CommonJS config files (e.g. prettier.config.cjs)
|
|
34
|
+
{
|
|
35
|
+
files: ['**/*.cjs'],
|
|
36
|
+
languageOptions: {
|
|
37
|
+
sourceType: 'commonjs',
|
|
38
|
+
globals: { ...globals.node },
|
|
39
|
+
},
|
|
40
|
+
},
|
|
41
|
+
|
|
42
|
+
// Project-wide language settings and small React tweaks
|
|
43
|
+
{
|
|
44
|
+
files: ['**/*.{js,jsx,ts,tsx}'],
|
|
45
|
+
languageOptions: {
|
|
46
|
+
ecmaVersion: 'latest',
|
|
47
|
+
sourceType: 'module',
|
|
48
|
+
globals: { ...globals.browser, ...globals.node },
|
|
49
|
+
},
|
|
50
|
+
plugins: {
|
|
51
|
+
'react-hooks': pluginReactHooks,
|
|
52
|
+
},
|
|
53
|
+
settings: {
|
|
54
|
+
react: { version: 'detect' },
|
|
55
|
+
},
|
|
56
|
+
rules: {
|
|
57
|
+
// Not needed with React 17+ / automatic JSX runtime
|
|
58
|
+
'react/react-in-jsx-scope': 'off',
|
|
59
|
+
'react/jsx-uses-react': 'off',
|
|
60
|
+
// React Hooks rules with Recoil support
|
|
61
|
+
'react-hooks/rules-of-hooks': 'error',
|
|
62
|
+
'react-hooks/exhaustive-deps': [
|
|
63
|
+
'warn',
|
|
64
|
+
{
|
|
65
|
+
additionalHooks: '(useRecoilCallback|useRecoilTransaction_UNSTABLE)',
|
|
66
|
+
},
|
|
67
|
+
],
|
|
68
|
+
// Allow intentionally unused vars/args when prefixed with _
|
|
69
|
+
'no-unused-vars': 'off',
|
|
70
|
+
'@typescript-eslint/no-unused-vars': [
|
|
71
|
+
'warn',
|
|
72
|
+
{
|
|
73
|
+
varsIgnorePattern: '^_',
|
|
74
|
+
argsIgnorePattern: '^_',
|
|
75
|
+
caughtErrorsIgnorePattern: '^_',
|
|
76
|
+
},
|
|
77
|
+
],
|
|
78
|
+
|
|
79
|
+
'no-console': 'warn',
|
|
80
|
+
'no-debugger': 'error',
|
|
81
|
+
|
|
82
|
+
// TS strictness
|
|
83
|
+
'@typescript-eslint/consistent-type-imports': 'error',
|
|
84
|
+
'@typescript-eslint/no-explicit-any': 'warn',
|
|
85
|
+
},
|
|
86
|
+
},
|
|
87
|
+
|
|
88
|
+
// Disable formatting rules that conflict with Prettier
|
|
89
|
+
eslintConfigPrettier,
|
|
90
|
+
])
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
# Lighthouse CI config for the haus pre-push performance gate (haus.lefthook-lighthouse).
|
|
2
|
+
#
|
|
3
|
+
# lefthook builds the front end first; this file serves the build and measures it.
|
|
4
|
+
# REPLACE the server command, its ready line and the URLs with this project's own.
|
|
5
|
+
ci:
|
|
6
|
+
collect:
|
|
7
|
+
# A PRODUCTION build (`next start`, `vite preview`, `nuxt preview`), never the dev
|
|
8
|
+
# server: an unminified dev build scores far lower and says nothing about production.
|
|
9
|
+
# Pages that need data: serve them against a local fixture or seeded database, so the
|
|
10
|
+
# run needs no network. When that takes two servers, start them from one script that
|
|
11
|
+
# stops both when it is stopped, or one is left running on its port.
|
|
12
|
+
startServerCommand: npm run start
|
|
13
|
+
startServerReadyPattern: '[Rr]eady|Local:|[Ll]istening'
|
|
14
|
+
startServerReadyTimeout: 30000
|
|
15
|
+
# The pages that matter most: the start page and one page per template.
|
|
16
|
+
url:
|
|
17
|
+
- http://localhost:3000/
|
|
18
|
+
# Three runs per page. Each assertion reads the run most likely to pass (the default
|
|
19
|
+
# `optimistic` aggregation), so one noisy run does not fail a push.
|
|
20
|
+
numberOfRuns: 3
|
|
21
|
+
settings:
|
|
22
|
+
# Default emulation: mobile with simulated throttling, as PageSpeed Insights measures.
|
|
23
|
+
onlyCategories: [performance, accessibility, best-practices, seo]
|
|
24
|
+
assert:
|
|
25
|
+
assertions:
|
|
26
|
+
categories:performance: [error, { minScore: 0.9 }]
|
|
27
|
+
largest-contentful-paint: [error, { maxNumericValue: 2500 }]
|
|
28
|
+
cumulative-layout-shift: [error, { maxNumericValue: 0.1 }]
|
|
29
|
+
total-blocking-time: [error, { maxNumericValue: 300 }]
|
|
30
|
+
categories:accessibility: [warn, { minScore: 0.9 }]
|
|
31
|
+
upload:
|
|
32
|
+
# Reports stay on this machine. Never `temporary-public-storage`: it publishes every
|
|
33
|
+
# report on a public URL.
|
|
34
|
+
target: filesystem
|
|
35
|
+
outputDir: .lighthouseci
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
# Ignore dependencies and builds
|
|
2
|
+
node_modules
|
|
3
|
+
dist
|
|
4
|
+
build
|
|
5
|
+
coverage
|
|
6
|
+
.next
|
|
7
|
+
out
|
|
8
|
+
storybook-static
|
|
9
|
+
|
|
10
|
+
# Ignore config and env
|
|
11
|
+
.env*
|
|
12
|
+
package-lock.json
|
|
13
|
+
pnpm-lock.yaml
|
|
14
|
+
yarn.lock
|
|
15
|
+
|
|
16
|
+
# Ignore generated files
|
|
17
|
+
*.min.js
|
|
18
|
+
*.min.css
|
|
19
|
+
|
|
20
|
+
# Ignore IDE and system files
|
|
21
|
+
.vscode
|
|
22
|
+
.cursor
|
|
23
|
+
.claude
|
|
24
|
+
.DS_Store
|
|
25
|
+
.idea
|
|
26
|
+
|
|
27
|
+
# Ignore docs or exports
|
|
28
|
+
CHANGELOG.md
|
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
format: 1
|
|
2
|
+
upstreams:
|
|
3
|
+
superpowers:
|
|
4
|
+
repo: https://github.com/obra/superpowers.git
|
|
5
|
+
tag: v6.4.2
|
|
6
|
+
commit: 8ca22dba9a94f28898bbce59f2537ff4d87c747d
|
|
7
|
+
mattpocock:
|
|
8
|
+
repo: https://github.com/mattpocock/skills.git
|
|
9
|
+
commit: 4588b32ecab9ecc9fc8cc6b6c5e7d675b6004b0d
|
|
10
|
+
ecc:
|
|
11
|
+
repo: https://github.com/affaan-m/ECC.git
|
|
12
|
+
commit: ef648e01899ba3e8dc6371642deaaf64b4477775
|
|
13
|
+
packages:
|
|
14
|
+
software-engineering:
|
|
15
|
+
routing:
|
|
16
|
+
- 'adr-decisions: not for trivial edits with no architectural consequence.'
|
|
17
|
+
- 'issue-authoring: not for work already approved and planned, that belongs in the plan.'
|
|
18
|
+
- "writing-documentation: not for code changes with no documentation impact, or where facts would have to be invented. The glossary and the writing style guide are other skills' jobs."
|
|
19
|
+
- "whats-installed: not for installing, removing or updating items, that is the haus CLI's job, not a conversation."
|
|
20
|
+
- 'haus-workflow: use for haus tasks (init, clone, new, doctor, refresh, uninstall, help); not for code changes in the project itself.'
|
|
21
|
+
- 'package-manager-yarn4-pnpm89: not for feature-only code edits with no dependency or workspace impact.'
|
|
22
|
+
- 'issue-creator: not for repos without GitHub issues enabled, or where issue hygiene is managed elsewhere.'
|
|
23
|
+
skills:
|
|
24
|
+
- adr-decisions
|
|
25
|
+
- issue-authoring
|
|
26
|
+
- writing-documentation
|
|
27
|
+
- whats-installed
|
|
28
|
+
- haus-workflow
|
|
29
|
+
- package-manager-yarn4-pnpm89
|
|
30
|
+
agents:
|
|
31
|
+
- issue-creator
|
|
32
|
+
upstream:
|
|
33
|
+
- from: superpowers
|
|
34
|
+
plugin: true
|
|
35
|
+
- from: mattpocock
|
|
36
|
+
skills:
|
|
37
|
+
- skills/productivity/grilling
|
|
38
|
+
- skills/engineering/domain-modeling
|
|
39
|
+
- skills/engineering/grill-with-docs
|
|
40
|
+
- skills/engineering/research
|
|
41
|
+
- skills/productivity/handoff
|
|
42
|
+
- skills/engineering/retro
|
|
43
|
+
- skills/productivity/writing-for-agents
|
|
44
|
+
- skills/engineering/improve-codebase-architecture
|
|
45
|
+
- skills/engineering/codebase-design
|
|
46
|
+
- skills/engineering/wayfinder
|
|
47
|
+
- from: ecc
|
|
48
|
+
agents:
|
|
49
|
+
- agents/typescript-reviewer.md
|
|
50
|
+
- agents/react-reviewer.md
|
|
51
|
+
- agents/security-reviewer.md
|
|
52
|
+
client-requests:
|
|
53
|
+
skills:
|
|
54
|
+
- request
|
|
55
|
+
- request-assess-impact
|
|
56
|
+
- request-score
|
|
57
|
+
- request-sync
|
|
58
|
+
- request-write-spec
|
|
59
|
+
agents:
|
|
60
|
+
- request-assessor
|
|
61
|
+
- request-design-reviewer
|
|
62
|
+
- request-designer
|
|
63
|
+
- request-scorer
|
|
64
|
+
- request-specifier
|
|
65
|
+
- request-specifier-eskalerad
|
|
66
|
+
communication:
|
|
67
|
+
skills: [slack-cowork]
|
|
68
|
+
web-react:
|
|
69
|
+
skills: [react-router-v7-patterns, i18next-patterns, nextauth-patterns]
|
|
70
|
+
commerce-vendure:
|
|
71
|
+
skills: [vendure-app-patterns, vendure-plugin-patterns, bullmq-patterns, qliro-patterns]
|
|
72
|
+
wordpress:
|
|
73
|
+
skills: [wordpress-bedrock-patterns, wordpress-acf-elementor-jetengine-patterns]
|
|
74
|
+
laravel:
|
|
75
|
+
skills: [laravel-nova-patterns]
|
|
76
|
+
dotnet:
|
|
77
|
+
skills: [auth-oidc-azure-bankid-patterns]
|
|
78
|
+
strapi:
|
|
79
|
+
skills: [strapi-patterns]
|
|
80
|
+
nx:
|
|
81
|
+
skills: [nx-tag-conventions]
|
|
@@ -0,0 +1,114 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: adr-decisions
|
|
3
|
+
description: >-
|
|
4
|
+
Draft and gate Architecture Decision Records (ADRs) when changes are decision-worthy.
|
|
5
|
+
Use when `haus decisions suggest` fires, when adding deps/schema/auth/API changes,
|
|
6
|
+
or when the user asks why a choice was made. Machine drafts; human approves.
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
# ADR decisions
|
|
10
|
+
|
|
11
|
+
Captures **why** significant choices were made under `docs/decisions/`.
|
|
12
|
+
|
|
13
|
+
## Use when
|
|
14
|
+
|
|
15
|
+
- `haus decisions suggest` or the Stop hook proposes an ADR
|
|
16
|
+
- A change touches dependencies, schema, auth, public APIs, CI, or infrastructure
|
|
17
|
+
- The user asks "why did we choose X?" before coding an alternative
|
|
18
|
+
|
|
19
|
+
## When to skip
|
|
20
|
+
|
|
21
|
+
Gate carve-outs live in the haus CLI algorithm (not `decisions-triggers.json`). Use this table:
|
|
22
|
+
|
|
23
|
+
| Change | ADR needed? |
|
|
24
|
+
| --------------------------------------------------------------------- | ------------------------------------------ |
|
|
25
|
+
| Dependency version bump, no dep added/removed | No |
|
|
26
|
+
| New or removed dependency | Yes |
|
|
27
|
+
| Lockfile-only regen (no package.json change) | No |
|
|
28
|
+
| Catalog sync (`chore/sync-catalog-*` branch, or `library/catalog/**`) | No |
|
|
29
|
+
| Schema/migration/CI/infra/API-contract/auth path | Yes (security paths: `[adr-skip]` ignored) |
|
|
30
|
+
| 8+ files across 2+ top-level dirs (not a dep bump) | Yes |
|
|
31
|
+
| Docs/tests-only | No (already exempt) |
|
|
32
|
+
|
|
33
|
+
To waive the trigger rules, put `[adr-skip] <reason>` on its own line in the PR body or in a commit body, not the subject. A mention mid-line or in backticks does not count (CLI 5.11.0 and later). It never waives a misplaced or invalid record.
|
|
34
|
+
|
|
35
|
+
## Workflow
|
|
36
|
+
|
|
37
|
+
1. Run `haus decisions suggest` (or use the Stop-hook JSON draft).
|
|
38
|
+
2. Write `docs/decisions/NNNN-slug.md` with status Proposed and add a README index row with a one-line **why**.
|
|
39
|
+
3. Ask the user for approval (see below). **Never** mark `Accepted` without explicit approval.
|
|
40
|
+
4. On approval: set the status to Accepted in the record and its index row. Nothing else in the record changes.
|
|
41
|
+
5. Commit the ADR in the same PR as the code change.
|
|
42
|
+
|
|
43
|
+
### Asking for approval
|
|
44
|
+
|
|
45
|
+
An approval ask carries, in the message itself:
|
|
46
|
+
|
|
47
|
+
1. The decision in one sentence.
|
|
48
|
+
2. What the human already decided, quoted from them, or `nothing` when they decided nothing. Never paraphrase your own reasoning as their quote.
|
|
49
|
+
3. Your own choices, numbered so each can be approved or rejected alone, each with its main rejected alternative.
|
|
50
|
+
4. What approval changes: status Proposed to Accepted in the record and its index row, nothing else.
|
|
51
|
+
|
|
52
|
+
```text
|
|
53
|
+
Approve ADR-0034 (status Proposed to Accepted, nothing else changes).
|
|
54
|
+
Decision: product pages live under /products/<slug>.
|
|
55
|
+
You decided: "keep the old URLs working" (redirects).
|
|
56
|
+
My choices, approve or reject each:
|
|
57
|
+
1. Path is /products, not /p. Rejected: /p, shorter but opaque.
|
|
58
|
+
2. Query keys in English. Rejected: Swedish keys, they leak into shared links.
|
|
59
|
+
3. Permanent redirects (308) from old paths. Rejected: 302, search engines never move.
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
## Do not
|
|
63
|
+
|
|
64
|
+
- Ask for approval with only an ADR number or link
|
|
65
|
+
- Hand-author ADRs without pulling context from the diff and conversation
|
|
66
|
+
- Skip the README index update
|
|
67
|
+
- Reach for `[adr-skip]` on security/auth paths — the gate ignores it; write the ADR instead
|
|
68
|
+
|
|
69
|
+
## Commands
|
|
70
|
+
|
|
71
|
+
```bash
|
|
72
|
+
haus decisions suggest # draft from staged/unstaged diff
|
|
73
|
+
haus decisions check --staged # local gate
|
|
74
|
+
haus decisions next-number # next NNNN
|
|
75
|
+
haus decisions validate path # structure check
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
Index lives at `docs/decisions/README.md` — keep it `@import`ed from `CLAUDE.md`.
|
|
79
|
+
|
|
80
|
+
## When another skill offers an ADR, or the decision has no diff
|
|
81
|
+
|
|
82
|
+
Another skill (for example `domain-modeling`, or a skill that calls it) may tell you to record or offer an ADR in its own format and folder. In this repo that skill only decides whether the decision deserves a record. You write the record here: (1) run `haus decisions next-number` for the number; `haus decisions suggest` prints nothing without a decision-worthy diff, so do not wait for it; (2) create `docs/decisions/NNNN-kebab-case-title.md` from the template below; (3) add its row to `docs/decisions/README.md`; (4) status is Proposed until a human approves, asked for as under Asking for approval. Never create `docs/adr/`.
|
|
83
|
+
|
|
84
|
+
### Template
|
|
85
|
+
|
|
86
|
+
```markdown
|
|
87
|
+
# ADR-NNNN: [Short title]
|
|
88
|
+
|
|
89
|
+
- **Status:** Proposed | Accepted | Superseded by ADR-XXXX | Deprecated
|
|
90
|
+
- **Date:** YYYY-MM-DD
|
|
91
|
+
- **Decided by:** [person who approved] (draft by [AI agent])
|
|
92
|
+
- **Affects:** [components/paths/packages]
|
|
93
|
+
- **Related:** [PR link, issue, related ADR numbers]
|
|
94
|
+
|
|
95
|
+
## Context
|
|
96
|
+
|
|
97
|
+
What problem or situation triggered the decision? What constraints applied?
|
|
98
|
+
|
|
99
|
+
## Decision
|
|
100
|
+
|
|
101
|
+
What we chose, in plain language — ideally one sentence.
|
|
102
|
+
|
|
103
|
+
## Motivation (why)
|
|
104
|
+
|
|
105
|
+
Why this over the alternatives. **This is the line agents read to answer "why".**
|
|
106
|
+
|
|
107
|
+
## Alternatives considered
|
|
108
|
+
|
|
109
|
+
- [Alternative] — rejected because [reason].
|
|
110
|
+
|
|
111
|
+
## Consequences
|
|
112
|
+
|
|
113
|
+
Positive and negative follow-ons. What becomes harder? What do we lock in?
|
|
114
|
+
```
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: auth-oidc-azure-bankid-patterns
|
|
3
|
+
description: Enterprise auth router for OIDC, Azure AD, BankID, and SAML2 identity flows.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Enterprise Auth Patterns (OIDC / Azure AD / BankID / SAML2)
|
|
7
|
+
|
|
8
|
+
## Use when
|
|
9
|
+
|
|
10
|
+
- task modifies login/session/token/claims or external identity provider integration
|
|
11
|
+
- task touches auth middleware/guards, callback handlers, or identity config
|
|
12
|
+
- task wires or modifies SAML2 SP/IDP metadata, ACS endpoints, or assertion validation (e.g. Laravel `24slides/laravel-saml2`)
|
|
13
|
+
|
|
14
|
+
## Do not use when
|
|
15
|
+
|
|
16
|
+
- task is generic user profile CRUD with no auth protocol change
|
|
17
|
+
- task is unrelated to identity, tokens, or access policy
|
|
18
|
+
- task is `next-auth` / `@auth/core` session work (use `nextauth-patterns`)
|
|
19
|
+
|
|
20
|
+
## Inspect first
|
|
21
|
+
|
|
22
|
+
- auth guard/middleware and session/token handling files
|
|
23
|
+
- OIDC/Azure/BankID provider config and callback handlers
|
|
24
|
+
- SAML2 config files: SP entityId, ACS URL, IDP metadata XML, certificate fingerprint
|
|
25
|
+
- claim/role mapping logic and downstream authorization checks
|
|
26
|
+
|
|
27
|
+
## Avoid mistakes
|
|
28
|
+
|
|
29
|
+
- accepting unvalidated tokens/claims
|
|
30
|
+
- changing redirect/callback URLs without env/config alignment
|
|
31
|
+
- mixing authentication identity with authorization policy logic
|
|
32
|
+
- accepting SAML assertions without signature validation or with mismatched audience/issuer
|
|
33
|
+
- shipping SAML SP private keys or IDP shared secrets in repo
|
|
34
|
+
|
|
35
|
+
## Router
|
|
36
|
+
|
|
37
|
+
1. Load `references/conventions.md` for naming, do/don't, and forbidden patterns.
|
|
38
|
+
2. Load `references/scope.md` for provider integration touchpoints.
|
|
39
|
+
3. Load `references/workflow.md` only for auth flow and failure path tracing.
|
|
40
|
+
4. Validate token/session lifecycle and permission impact.
|
|
41
|
+
|
|
42
|
+
## References
|
|
43
|
+
|
|
44
|
+
- references/conventions.md
|
|
45
|
+
- references/scope.md
|
|
46
|
+
- references/workflow.md
|
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
## Naming conventions
|
|
2
|
+
|
|
3
|
+
- Callback handlers: `handleCallback`, `handleLogout`, `handleSilentRenew`
|
|
4
|
+
- Token utilities in `lib/auth/` — e.g. `lib/auth/tokenUtils.ts`, `lib/auth/sessionUtils.ts`
|
|
5
|
+
- Claims mappers in `lib/claims/` — e.g. `lib/claims/azureClaimsMapper.ts`, `lib/claims/bankIdClaimsMapper.ts`
|
|
6
|
+
- OIDC config objects: `oidcConfig`, `azureAdConfig`, `bankIdConfig` (camelCase, provider-prefixed)
|
|
7
|
+
- Middleware/guard files: `authGuard.ts`, `oidcMiddleware.ts` (lowercase-hyphen or camelCase)
|
|
8
|
+
- Session cookie name constant: `SESSION_COOKIE_NAME` (SCREAMING_SNAKE for constants)
|
|
9
|
+
|
|
10
|
+
## Do / don't
|
|
11
|
+
|
|
12
|
+
DO: Validate `state` and `nonce` server-side on every callback — DON'T: trust client-supplied state without comparing to server session value
|
|
13
|
+
DO: Use PKCE (`code_challenge` + `code_verifier`) for all public/SPA clients — DON'T: use implicit flow; it exposes tokens in URL fragments
|
|
14
|
+
DO: Store session identifiers in `httpOnly`, `Secure`, `SameSite=Lax` cookies — DON'T: store access tokens or refresh tokens in `localStorage` or `sessionStorage`
|
|
15
|
+
DO: Verify `iss` and `aud` claims when validating tokens — DON'T: trust `sub` claim without confirming the issuer matches the configured provider
|
|
16
|
+
DO: Rotate session identifier after successful authentication (session fixation protection) — DON'T: reuse pre-auth session ID post-login
|
|
17
|
+
DO: Use short-lived access tokens and refresh via server-side token exchange — DON'T: set access token TTL > 15 minutes for sensitive resources
|
|
18
|
+
DO: Log auth events (login success, logout, token refresh) without token/claim values — DON'T: log raw tokens, claims payloads, or `id_token` strings
|
|
19
|
+
DO: Derive `redirect_uri` from server-side config only — DON'T: accept `redirect_uri` from query params or user-controlled input
|
|
20
|
+
|
|
21
|
+
## Forbidden patterns
|
|
22
|
+
|
|
23
|
+
NEVER: Construct `redirect_uri` from user-supplied query parameters — open redirect vulnerability
|
|
24
|
+
NEVER: Skip token signature validation in tests — establishes false confidence in auth flow
|
|
25
|
+
NEVER: Decode JWT without verifying signature (e.g. `jwt.decode()` without `jwt.verify()`) — tokens can be forged
|
|
26
|
+
NEVER: Store BankID personal number in session beyond immediate verification — PII retention risk
|
|
27
|
+
NEVER: Catch and swallow auth errors silently — auth failures must surface or be logged
|
|
28
|
+
NEVER: Return full claims object in API response — expose only mapped, required attributes
|
|
29
|
+
NEVER: Use `alg: none` or skip algorithm validation in JWT verification — critical security bypass
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
# Scope
|
|
2
|
+
|
|
3
|
+
## In-scope files and dirs
|
|
4
|
+
|
|
5
|
+
- `src/auth/**` — auth guards, strategies, decorators, session handlers
|
|
6
|
+
- `src/middleware/auth.*` — request-level auth middleware
|
|
7
|
+
- `config/auth.*`, `config/oidc.*`, `config/azure-ad.*` — provider configuration
|
|
8
|
+
- `src/**/callback.*`, `src/**/redirect.*` — OIDC/BankID callback handlers
|
|
9
|
+
- `src/**/claims.*`, `src/**/roles.*` — claim extraction and role mapping
|
|
10
|
+
- `src/**/token.*` — token validation, refresh, introspection
|
|
11
|
+
- `.env*` — provider client IDs, secrets, tenant IDs, redirect URIs
|
|
12
|
+
- `src/**/session.*` — session store and cookie settings
|
|
13
|
+
|
|
14
|
+
## Stack boundaries
|
|
15
|
+
|
|
16
|
+
- OIDC/OpenID Connect: authorization code flow, PKCE, token exchange
|
|
17
|
+
- Azure AD: app registrations, tenant config, app roles, group claims
|
|
18
|
+
- BankID: personal number assertion, signed assertions, auth level handling
|
|
19
|
+
- Not in scope: generic user CRUD with no identity protocol contract change
|
|
20
|
+
- Not in scope: database schema changes not driven by auth claim mapping
|
|
21
|
+
|
|
22
|
+
## Triggers
|
|
23
|
+
|
|
24
|
+
- Adding or modifying OIDC provider (tenant ID, client ID, scopes)
|
|
25
|
+
- Changing redirect/callback URIs or post-login redirect logic
|
|
26
|
+
- Adding new claim/role mappings to downstream authorization checks
|
|
27
|
+
- Switching session storage backend (Redis, DB, cookie)
|
|
28
|
+
- Changing token validation library or JWT verification logic
|
|
29
|
+
- Adding BankID personal number assertion or auth level check
|
|
30
|
+
- Touching auth guard on any route/resolver/controller
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
# Workflow
|
|
2
|
+
|
|
3
|
+
## Implementation steps
|
|
4
|
+
|
|
5
|
+
1. Identify provider: OIDC generic, Azure AD (v1/v2 endpoint), or BankID — check existing config files
|
|
6
|
+
2. Locate auth middleware/guard chain — map which routes/resolvers it protects
|
|
7
|
+
3. Check callback handler: verify state/nonce validation, PKCE verifier, token endpoint call
|
|
8
|
+
4. Trace claim extraction: from `id_token` or `userinfo` endpoint to application user object
|
|
9
|
+
5. Validate role/permission mapping: confirm downstream authorization checks match new claims
|
|
10
|
+
6. Verify redirect URI alignment: env vars, provider app registration, and middleware matcher all consistent
|
|
11
|
+
7. Check token storage: httpOnly cookie vs session store — confirm expiry and refresh logic
|
|
12
|
+
8. For BankID: verify personal number assertion is validated before trust, check auth level (`loa`)
|
|
13
|
+
9. Run auth flow end-to-end in dev environment: login → callback → session → protected route
|
|
14
|
+
|
|
15
|
+
## Commands
|
|
16
|
+
|
|
17
|
+
```bash
|
|
18
|
+
# NestJS/Node
|
|
19
|
+
yarn tsc --noEmit # type check token/claims types
|
|
20
|
+
jest --testPathPattern auth # run auth unit tests
|
|
21
|
+
|
|
22
|
+
# Laravel (Socialite / Laravel Passport)
|
|
23
|
+
php artisan test --filter=Auth # run auth feature tests
|
|
24
|
+
php artisan route:list | grep callback # inspect registered callback routes
|
|
25
|
+
|
|
26
|
+
# .NET
|
|
27
|
+
dotnet test --filter Category=Auth
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
## Validation checklist
|
|
31
|
+
|
|
32
|
+
- [ ] Token signature verified against provider JWKS endpoint — never skip
|
|
33
|
+
- [ ] `state` and `nonce` parameters validated on callback to prevent CSRF/replay
|
|
34
|
+
- [ ] Redirect URIs match exactly (no trailing slash drift) in env and provider config
|
|
35
|
+
- [ ] Session expiry and refresh token rotation implemented for long-lived sessions
|
|
36
|
+
- [ ] Role/claim mapping tested with both positive and negative claim values
|
|
37
|
+
- [ ] BankID `loa` level meets application minimum assurance requirement
|
|
38
|
+
- [ ] Auth guard applied to all protected routes — no accidental public exposure
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: bullmq-patterns
|
|
3
|
+
description: BullMQ router. Use for queue definitions, workers, schedulers, repeatable jobs, and graceful shutdown.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# BullMQ Patterns
|
|
7
|
+
|
|
8
|
+
## Use when
|
|
9
|
+
|
|
10
|
+
- task adds, modifies, or removes a BullMQ queue, worker, scheduler, or flow
|
|
11
|
+
- task touches Redis connection wiring for BullMQ (`new Queue("name", { connection })`)
|
|
12
|
+
- task adds repeatable jobs (cron, every-N-ms) or delayed jobs
|
|
13
|
+
- task wires graceful shutdown (worker drain, queue close) into app lifecycle
|
|
14
|
+
|
|
15
|
+
## Do not use when
|
|
16
|
+
|
|
17
|
+
- project uses a different job system (Bull v3, Agenda, custom in-process scheduler)
|
|
18
|
+
- task is in-process scheduling without Redis (use a different skill)
|
|
19
|
+
- task is Redis general usage with no BullMQ surface (use `haus.ecc-redis-patterns`)
|
|
20
|
+
|
|
21
|
+
## Inspect first
|
|
22
|
+
|
|
23
|
+
- Queue definitions: `queues/*.ts` or `src/queues/*.ts`
|
|
24
|
+
- Worker definitions: `workers/*.ts` — `new Worker(name, processor, { connection })`
|
|
25
|
+
- Shared Redis connection module: typically `lib/redis.ts` (must be `IORedis` instance for BullMQ)
|
|
26
|
+
- App lifecycle: where workers start, where they're closed on `SIGTERM` / `SIGINT`
|
|
27
|
+
- `package.json` BullMQ version — 5.x has breaking changes vs 4.x
|
|
28
|
+
|
|
29
|
+
## Avoid mistakes
|
|
30
|
+
|
|
31
|
+
- creating multiple `IORedis` connections — BullMQ requires a separate connection per Queue/Worker
|
|
32
|
+
- using `Redis` from `redis` package (node-redis) — BullMQ requires `IORedis`
|
|
33
|
+
- mixing `bull` v3 and `bullmq` packages — different APIs, can't share queues
|
|
34
|
+
- forgetting `concurrency` on `Worker` — defaults to 1, blocks throughput
|
|
35
|
+
- not closing workers on shutdown — jobs marked failed when worker disappears
|
|
36
|
+
- swallowing job errors in the processor — failed jobs disappear silently
|
|
37
|
+
|
|
38
|
+
## Router
|
|
39
|
+
|
|
40
|
+
1. Load `references/conventions.md` for queue, worker, and connection patterns.
|
|
41
|
+
2. Load `references/scope.md` for in-scope files and stack boundaries.
|
|
42
|
+
3. Load `references/workflow.md` only for graceful shutdown and job retry diagnosis.
|
|
43
|
+
4. Keep one queue per concern; share `IORedis` instances per role (Queue vs Worker).
|
|
44
|
+
|
|
45
|
+
## References
|
|
46
|
+
|
|
47
|
+
- references/conventions.md
|
|
48
|
+
- references/scope.md
|
|
49
|
+
- references/workflow.md
|
|
50
|
+
|
|
51
|
+
## Reference Documentation
|
|
52
|
+
|
|
53
|
+
Up-to-date API docs are cached locally by haus.
|
|
54
|
+
|
|
55
|
+
To refresh (uses etag — fast if unchanged):
|
|
56
|
+
|
|
57
|
+
```bash
|
|
58
|
+
haus fetch-refs --id haus.bullmq-patterns
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
Then read `.haus-workflow/llms-cache/docs-bullmq-io-llms-txt.md` for current API reference.
|
|
62
|
+
|
|
63
|
+
Source: https://docs.bullmq.io/llms.txt
|