ai first agents

46 tagged ai first, measured the same way as everything else here.

Browse within: Multi-Agent 15adversarial 15agent-friendly 11better-auth 11cloudflare-workers 11agentic-design-patterns 10agentic-development 10agentic-workflow 10ai-developer-tools 10agile 8ai-driven 8development-framework 8documentation 8software-architecture 8

ac-adversary

04

harness-studio/harness-studio

Agent Claude Code

Attacks acceptance criteria — testability, completeness, edges, concurrency. Phase-1 gate.

9 2mo ago A 24 tokens original MIT

product-analyst

05

harness-studio/harness-studio

Agent Claude Code

Turns a raw brief/overview into a structured problem statement; with split mode, decomposes it into work items. Separates problem from solution.

9 2mo ago A 34 tokens original MIT

test-author

06

harness-studio/harness-studio

Agent Claude Code

Writes the failing tests (the RED step of TDD) from the locked acceptance criteria, before any implementation exists. Maker of tests only — never writes production code.

9 2mo ago A 36 tokens original MIT

claim-verifier

07

synaptiai/synapti-marketplace

Agent

Use after NCI analysis to fact-check key claims and update manipulation scores based on verification results. Auto-invoked by /decipon:verify command.

6 28d ago A 36 tokens original Apache-2.0

nci-analyzer

08

synaptiai/synapti-marketplace

Agent

Use when user asks to analyze content for manipulation, propaganda, disinformation patterns, or requests NCI scoring. Auto-invoked by /decipon:analyze command.

6 28d ago A 41 tokens original Apache-2.0

synaptiai/synapti-marketplace

Agent

Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.

6 28d ago A 36 tokens original Apache-2.0

README

10

SeanningTatum/cf-saas-starter-react-router

Agent Claude Code

Project-local Claude Code subagents that wrap pieces of .brain/HARNESS.md. The main thread delegates to these so it doesn't have to re-load harness rules every turn.

5 25d ago A 0 tokens

feature-verifier

11

SeanningTatum/cf-saas-starter-react-router

Agent Claude Code

Drives a feature's golden path + one error path through the LIVE app using the Playwright CLI (a throwaway Node script run headless), screenshots each step, and writes a verification doc to .brain/features/ /verifications/ .md. Replaces writing per-feature e2e specs. Use for any user-visible feature/flow before…

5 25d ago A 131 tokens

ui-builder

12

SeanningTatum/cf-saas-starter-react-router

Agent Claude Code

Builds and changes UI in this repo — routes, components, marketing surfaces, forms, tables, empty/loading/error states. Carries the frontend rules, the craft moves and the anti-slop tells so the mistakes are not made in the first place, and self-measures with design:audit before returning. Use for ANY user-visible…

5 25d ago A 159 tokens