beerandcodeteam

27 mods across 2 repositories, 54 stars between them.

bc-harness

02

beerandcodeteam/beer-and-code-harness

Plugin Claude Code

Beer and Code harness — commands, scripts, and hooks to help developers build robust, scalable, tested, real-world-proven projects.

43 13d ago A tokens not measured original MIT

ai-context-core

03

beerandcodeteam/beer-and-code-harness

Agent

Writer agent for the /ai-context pipeline. Generates or refreshes AGENTS.md and CLAUDE.md in the target repo from the inspector digest. Idempotent — diffs against on-disk bytes, writes only when content changed, respects the ownership contract. Use only as step 4 of /ai-context.

43 13d ago A 68 tokens original MIT

ai-context-docs

04

beerandcodeteam/beer-and-code-harness

Agent

Writer agent for the /ai-context pipeline. Generates or refreshes the 8 docs/agents/.md files describing the implemented code as it is (AS IS only — no prescriptive layers). Idempotent — diffs against on-disk bytes, writes only when content changed, respects the ownership contract. Use only as step 4 of /ai-context.

43 13d ago A 78 tokens original MIT

beerandcodeteam/beer-and-code-harness

Agent

Read-only repo inspector for the /ai-context pipeline. Sweeps the implemented code (never .spec) and returns a structured digest — stack, commands, layout, signals, artifact ownership — that the writer agents consume verbatim. Use only as step 3 of /ai-context.

43 13d ago A 62 tokens original MIT

clarifier

06

beerandcodeteam/beer-and-code-harness

Agent

Adversarial requirements QA for the /plan pipeline (step 6). Two modes — analyze (find ambiguities, gaps, contradictions in SPEC.md and return prioritized questions) and resolve (apply developer answers in-place, increment version). Never talks to the developer directly; the router owns the conversation. Use only as…

43 13d ago A 73 tokens original MIT

planner

07

beerandcodeteam/beer-and-code-harness

Agent

Read-only planning lead for the /plan pipeline (step 7). Produces PLAN.md — architecture-aware task decomposition with dependency phases, risks, validation criteria — plus PHASES.md (ralph.sh-executable view) and conditionally formal contracts (OpenAPI/gRPC/AsyncAPI) from SPEC RIGID. Use only as step 7 of /plan.

43 13d ago A 77 tokens original MIT

specifier

08

beerandcodeteam/beer-and-code-harness

Agent

Requirements engineer for the /plan pipeline (step 5). Transforms a confirmed developer description + ACs into a formal SPEC.md with GEARS syntax, RIGID/FLEXIBLE sections, AS IS / TO BE diagrams, and binary acceptance criteria. Use only as step 5 of /plan.

43 13d ago A 63 tokens original MIT

ai-context

09

beerandcodeteam/beer-and-code-harness

Command

Generate or refresh the canonical AGENTS context tree (AGENTS.md, CLAUDE.md, docs/agents/.md) from the implemented code. Idempotent upsert — safe to re-run; updates only what drifted. Documents reality only; never reads .spec.

43 13d ago A 56 tokens original MIT

init

10

beerandcodeteam/beer-and-code-harness

Command

Show the status of the init spec chain (.spec/init/) — present, absent, or stale — and run the next init: command in the chain. Writes nothing itself; all authoring lives in the invoked init: commands.

43 13d ago A 47 tokens original MIT

plan

11

beerandcodeteam/beer-and-code-harness

Command

Planning pipeline — produces a formal SPEC.md (GEARS RIGID/FLEXIBLE), resolved clarifications, PLAN.md, and optional contracts from a developer-provided description. Writes only under .spec/features/[slug]/; never writes application code.

43 13d ago A 50 tokens original MIT

PreToolUse

12

beerandcodeteam/beer-and-code-harness

Hook

Runs before the agent uses a tool for Bash tool calls, executing sail-guard.sh. From beerandcodeteam/beer-and-code-harness.

43 13d ago A tokens not measured original MIT

ai-sdk-development

13

beerandcodeteam/worthly-api

Skill Claude CodeCodex

TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK. Activate when building, editing AI agents, chatbots, text generation, image generation, audio/TTS, transcription/STT, embeddings, RAG, vector stores, reranking, structured output, streaming, conversation memory, tools, queueing…

11 3mo ago A 146 tokens

beerandcodeteam/worthly-api

Skill Claude CodeCodex

Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization…

11 3mo ago A 114 tokens

pest-testing

15

beerandcodeteam/worthly-api

Skill Claude CodeCodex

Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to…

11 3mo ago A 171 tokens

test-runner

17

beerandcodeteam/worthly-api

Command Claude Code

USE THIS SUBAGENT ANY TIME you need to run Pest tests, validate a fix, check the full suite, or filter tests. Returns a compact summary (max 20 lines) even when many tests fail. NEVER writes code.

11 3mo ago A 51 tokens

PreToolUse

18

beerandcodeteam/worthly-api

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing block-non-sail.sh and log-event.sh (2 commands). From beerandcodeteam/worthly-api.

11 3mo ago A tokens not measured

PostToolUse

19

beerandcodeteam/worthly-api

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, executing pint-and-test.sh and log-event.sh (2 commands). From beerandcodeteam/worthly-api.

11 3mo ago A tokens not measured

Notification

20

beerandcodeteam/worthly-api

Hook Claude Code

Runs when the agent sends a notification, executing notify-n8n.sh. From beerandcodeteam/worthly-api.

11 3mo ago A tokens not measured

Stop

21

beerandcodeteam/worthly-api

Hook Claude Code

Runs when the agent finishes a response, executing notify-n8n.sh, log-event.sh and log-tokens.sh (3 commands). From beerandcodeteam/worthly-api.

11 3mo ago A tokens not measured

UserPromptSubmit

22

beerandcodeteam/worthly-api

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing log-event.sh. From beerandcodeteam/worthly-api.

11 3mo ago A tokens not measured

worthly-api

23

beerandcodeteam/worthly-api

Settings file Claude Code

Agent settings declaring 5 hook events (PreToolUse, PostToolUse, Notification, Stop).

11 3mo ago A tokens not measured

laravel-boost

24

beerandcodeteam/worthly-api

MCP server Claude CodeCodexCursor +2

MCP server "laravel-boost" as configured in beerandcodeteam/worthly-api. Launched with vendor/bin/sail artisan boost:mcp.

11 3mo ago A tokens not measured