bobbyjohnstx/tinycode

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

11Stars on the repository
16Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

effect

01

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Work with Effect v4 / effect-smol TypeScript code in this repo.

11 4d ago A 17 tokens copy · 91% MIT

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

11 4d ago A 68 tokens copy · 72% MIT

team

03

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Launch a multi-agent team to work on a task in parallel.

11 4d ago A 14 tokens original MIT

ai-slop-cleaner

04

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.

11 4d ago A 25 tokens original MIT

debug

06

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Isolate a single most-likely root cause for a known failure — reproduce narrowly, gather concrete evidence, recommend the smallest next fix. For competing hypotheses that need ranking, use trace instead.

11 4d ago A 41 tokens original MIT

deepinit

07

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Deep codebase initialization — generates a per-directory tree of parent-linked AGENTS.md files with merge-preserving regeneration (keeps sections), providing whole-repo coverage where the sibling init skill writes only a single root file.

11 4d ago C 52 tokens original MIT

mcp-setup

08

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Configure MCP servers via a guided menu — curated bundles (Context7, Exa, Filesystem, GitHub) or a custom stdio/HTTP server — using tinycode mcp add, with scope control, verification, and troubleshooting guidance.

11 4d ago A 53 tokens original MIT

remember

09

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Triage a session's findings across memory surfaces — classify each item and route it to the right destination (project memory, CLAUDE.md/AGENTS.md, or session notes) rather than dumping everything into one store.

11 4d ago A 46 tokens original MIT

tc-doctor

10

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Diagnose and fix tinycode environment issues — Ollama install, model health, tool-call capability, directories, agents, skills, connectivity, and container health.

11 4d ago E 35 tokens original MIT

trace

11

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Evidence-driven causal tracing with competing hypotheses, ranked evidence, and discriminating probes.

11 4d ago A 17 tokens original MIT

verify

12

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Confirm a change works before claiming completion — runs a tiered evidence ladder (existing tests → build → narrow commands → manual) and reports only what was actually proven, never bluffs completion.

11 4d ago A 39 tokens original MIT

agents-sdk

13

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.

11 4d ago A 59 tokens copy · 100% MIT

cloudflare

14

bobbyjohnstx/tinycode

Skill Claude CodeCodex

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.

11 4d ago A 68 tokens copy · 100% MIT