Triage and act on a code review without assuming the reviewer is right - verify each item against the actual code, apply the small/valid/uncontested fixes directly, escalate load-bearing or risky ones to the user as grounded options, then run the project's quality gates before reporting.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Review an idea, concept, system, or problem against Frederic Vester's 8 bio-cybernetic rules - map its feedback loops, score each rule (aligned/at-risk/violated), surface the highest-leverage fixes, and judge whether the design is viable or headed for runaway growth, brittleness, or collapse.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Generate a complete, cross-platform .devcontainer setup for any project: host git/Claude Code/Codex credentials mounted in and ready to go, mise as tool-version manager and task runner, language-tailored toolchains and caches, a doctor check/repair command, Anthropic cloud (claude.ai/code) bootstrap, and graceful…
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Run a rigorous, research-backed evaluation of a startup or business idea - adaptive founder interview, parallel deep research, adversarial fact-checking, a scored analysis.json separating attractiveness from conviction, a polished standalone HTML report, and a searchable index across all evaluations.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Produce a reliable, high-stakes-grade result for any task by treating the work as guilty until independent skeptics fail to break it - runs a dynamic many-subagent adversarial-verification Workflow that hunts ten specific failure modes (silent assumptions, hidden inconsistencies, sycophancy, subtle conceptual errors…
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Continuous Iterative Development (CID) for long-horizon projects: an autonomous loop of four fresh-context roles (update-state, define-next, advance, review) that advances a project in small verified increments toward a human-owned target, self-determines its phase (new/poc/mvp/stable), adjusts rigor per phase, and…
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Apply systems thinking to a problem or decision - classify it as clear, complicated, complex, or chaotic, diagnose it with the DART framework, surface hidden parts/connections/patterns and incentive/feedback traps, and recommend the action protocol that fits the system type.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Turn any agent into a kind, efficient, occasionally funny task companion for the Vikunja task manager: self-healing setup, token-efficient bundled CLI, two identity modes (user account or companion account), a daily pulse radar, and schedulable automation playbooks (groom, split, review, celebrate, unstick, triage).
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Generate and edit raster images through the Codex CLI's built-in imagegen tool on your ChatGPT subscription (no API key) - reference images, reusable art-style cards, exact-size post-processing, and every output stored with its prompt in a project-local cauldron/ folder.
★not rated 2 14d agoA
tokens not measured
originalMIT
Convene a council of 16 personality-typed subagents to debate a complex, many-sided question under coded rules of order - blind openings, an open floor where members bid for the right to speak, a clerk who keeps the debate on its real disagreements - and decide by consensus or vote.
★not rated 2 14d 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: