Quality-first harness for autonomous AI coding agents: deterministic gates + a default-FAIL evaluator in the close path of the loop, over a Beads task spine. Done is earned, not asserted. Unifies GSD + Beads; stack-agnostic.
★not rated 6 5mo agoA
tokens not measured
originalMIT
Pollinations AI for Claude Code CLI. Generate images, text, audio, video, and transcribe speech. BYOP OAuth login — users fund their own usage with pollen credits.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Capture clean, repeatable screenshots of a GUI desktop app (Cursor, IDEs, browsers) on an isolated Xvfb display: drive it with python-Xlib (XTEST), capture with ImageMagick, annotate with a highlight box, crop or arrow. For docs, courses and bug reports; never touches the operator's live :0 desktop.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Continuous agent orchestration where the plugin IS a schema and a set of skills — there is no CLI. tursodb already executes SQL, so guild members reach the board by writing their own SQL against a guide, and the guild's rules live IN the database: CHECK constraints are the status vocabularies, VIEWS are the derived r.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Scientific paper writing, source-traced review, and de-AI rewriting for top-tier journals (ApJ/MNRAS/PRD/JCAP-class) and NSF/NIH proposals. Ships 12 skills and 40 tools under one typed standard: scientific-integrity blockers that cannot be waived as style preferences, a zero-target L0 lexicon, ranked advisories…
Go-To-Market consultant for Claude Code: gtm-buddy router + adaptive pipeline jobs -> positioning -> offer -> leads -> content/copy -> channels -> email -> measurement, calibrated by business archetype (coaching, B2B SaaS, B2C/e-commerce, local service, established company without marketing) and stage…
★not rated 6▲
+1 5mo agoA
tokens not measured
originalMIT
A development workflow that walks every piece of work through the six Working Geniuses — Wonder, Invention, Discernment, Galvanizing, Enablement, Tenacity — every stage a command the user types, every checkpoint a live exchange.
★not rated 6
changed 7d agoA
tokens not measured
originalMIT
Multi-agent harness for Claude Code: Planner→Generator→Evaluator sprints executed as background dynamic workflows (Agent-tool fallback), fable/opus/sonnet/haiku model routing with per-role reasoning effort, harness-engineering framework for design/diagnosis, and Anthropic 2026-04-04 P-G-E pattern.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Emulates the reasoning habits of Claude Fable 5: plan before executing, evidence over memory, self-refutation, iterative verification until it passes, lead with the result, and scope discipline.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Dialectical blog-post pipeline: interrogate, critique, author, revise. CMS-agnostic; voice and audience are project-local.
★not rated 6 6mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: