agentic-ai agents

chinkan/RustFox

Agent Claude Code

Reviews code quality, architecture, and production readiness for a completed task. Use only after spec-compliance review passes. Expects WHATWASIMPLEMENTED, PLANORREQUIREMENTS, BASESHA, HEADSHA, DESCRIPTION from parent.

LinHao-city/StoryMind

Agent Codex

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

darecstowell/scratchboard

Agent

Tickets for this repo live as markdown files in .scratch/, and the board bakes them to the Pages demo on every push. The tickets are public copy.

pedrobraiti/vizier-trading-skill

Agent

Research-only market envoy for Vizier's breadth-discovery (manager) mode. Sweeps ONE coverage area of the market with Scout data tools and returns a structured candidate shortlist. It has NO execution tools — it cannot place an order — so it is safe to fan out across the market in parallel. Spawned by the Vizier…

AminulIslamSifat/Sable

Agent

You are an analysis specialist. You research topics via web search AND review code for bugs, quality, and improvements.

hybridlabor-api/bdb-dev-optimized-agent-skills

Agent Claude Code

Adversarial review of build-node output against the plan's stated contract, before Shipping runs its automated gate. Modeled on the doubt-driven-development discipline (see .agents/graph.md): reads the artifacts and the contract, never the implementer's claim that it's done, never their reasoning — passing the claim…

christopherlouet/claude-base

Agent Claude Code

Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.

ayeshakhalid192007-dev/graph-engineering-crash-course

Agent Claude Code

A validation agent for this pattern's output.

EricLortie/laborforge-release

Agent

Agent "EXTERNAL_PLATFORM_AGENT_OVERRIDE" from EricLortie/laborforge-release, covering external platform agent override (system agents), scope, current system-agent architecture (implemented), system agents live in ecosystem 1 (admin) and current override mechanism (implemented).

usetheokit/theokit

Agent

@theokit/sdk stopped reading /.claude/ unconditionally (theokit-sdk#524) and put it behind local.compatSources. This layer had no way to forward that, so an agent built here could not opt into the foreign dialect at all.

evoelsewhere/evoflux

Agent

Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.

leji-org/leji

Agent

Independently review a proposed change set before the owner approves it, restoring the at-the-gate perspective a second person would bring to a single-owner circle.

rizvee/multimodel-dev-os

Agent

When multiple AI tools work on the same codebase, they need.

All-The-Vibes/ATV-Phoenix

Agent

Cloud worker that makes bounded Phoenix changes and proves outcomes objectively.

corteshvictor/vichu-flow

Agent Claude Code

Adversarially reviews the implementation for one VichuFlow review stage. Invoked by the vichu-orchestrator skill. Judges correctness against the task and ends with a single structured-verdict JSON object.

nerellasraj21/ai_governance_framework

Agent

You are the Orchestrator Agent for {PROJECTNAME}. You manage the entire pipeline lifecycle — sequencing agents, enforcing gates, tracking feedback loops, managing state, and dispatching escalation notifications. You are the only agent that interacts with all other agents.

suhaas/earnings-edge

Agent Claude Code

Identifies secrets, unsafe code, and privilege escalation risks.

pillaiharish/opencode-ollama-steroids

Agent

You are the strict reviewer agent for a receipt-first OpenCode + Ollama workflow.

ApexIQ/skillsmith

Agent

Skillsmith provides 33+ specialized commands for high-fidelity engineering. Run these to maintain 100% architectural integrity.

brandonkindred/Khala-Agentic-AI-Teams

Agent

RefinementAgent.run() (via diffformat.difforfull) and DesignAgent.revise() — plus its internal self-revision loop in withselfreview() (via the since-removed diffformat.diffspecorfull) — both used to shrink round-over-round revision prompts by resending only a compact delta against the previous round's content. Both…

TrendTweekers/article-autopilot

Agent Claude Code

Reviews user-facing copy in the active language profile for style, consistency, terminology drift, surface-specific tone, and factual claims that need verification. Use after editing files containing user-facing strings (UI labels, error messages, marketing copy, articles, legal text, outbound messages). Returns…

adeelahmad/agentrc

Agent

Cross-sprint learning, curated at each retrospective. Entries are advisory and never relax an invariant. First agentic-agile session in this repo (Sprint 1); seeded from the 2026-07-02/03 docs+examples+spec audit that produced this work order.

adamoutler/joplin-server-vector-memory

Agent Gemini CLI

Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.

PralhadYadawad/avvarre

Agent Claude Code

AI code reviewer enforcing Google style guides across 21 languages/formats. Runs fix-verify loops, compressed task sync, and workspace heatmaps.