Autonomous state machine for cognitive continuity. Preserves session state before context compaction and restores it on session start. Features priority-based selective restore, token budget tracking, auto decision extraction, and state archiving. Based on Alan Turing's 1936 paper 'On Computable Numbers'.
★not rated 2 7mo agoA
tokens not measured
originalMIT
Documentation-first methodology and multi-agent toolchain for technical non-fiction long-form manuscripts. The Bernoulli-textbook approach: design spec and chapter plans drive the manuscript.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Legacy project onboarding for Claude Code — analyzes the codebase, generates a token-budgeted CLAUDE.md, wires 4 guard hooks, manages forbidden zones, and aligns CI with local commands. Default --local-only writes zero PROJECT files (no team pollution). Use when setting up Claude Code on a legacy project, configuring.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.
★not rated 2
changed 9d agoA
tokens not measured
originalMIT
A research toolkit based on a detective-style method for analyzing interviews, surveys, feedback, public opinion, literature, and competitor material. It includes tools for organizing sources, tracing evidence, writing analyses, and challenging conclusions.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Data-adaptive lifecycle marketing engine for Claude Code. Connects GA4 or other data sources (or just an industry), scores data quality, and generates a prioritized portfolio of customer journeys with channel-ready CRM copy.
★not rated 2 27d agoA
tokens not measured
originalMIT
Semantic linefeeds enforcement for code comments, doc comments, and docstrings across Go, C-family, Rust, Python, shell, SQL, Ruby, and more, plus Markdown, with adapters for Claude Code, Codex CLI, and opencode.
★not rated 2 22d agoA
tokens not measured
originalApache-2.0
A Claude Code slash command that rewrites your request into an optimized, reasoning-maximizing prompt — clarifying first only when the ask is ambiguous or risky — then carries it out. Ships /p: structured context, specificity, meta-instructions for extended thinking, robust skip-comments for literals, intent typing…
★not rated 2 2mo agoA
tokens not measured
originalMIT
Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core — hard-capped curated memory, FTS5 session search, staged review.
★not rated 2
changed yesterdayA
tokens not measured
AGPL-3.0
One-shot release pipeline: commit, push, PR, merge, and branch cleanup. Auto-adapts branch strategy -- git-flow (feature to develop to main) if a develop branch exists, otherwise GitHub Flow (feature to main). Runs a pre-merge gate bundle: functional check (verify.sh or the project's test command), security scan…
★not rated 2 1mo agoA
tokens not measured
originalMIT
Marketplace hosting the slopstop plugin: ticket-anchored AI development for Linear, JIRA, and GitHub Issues — TDD-first planning, scope control, adversarial review, and multi-agent orchestration.
Engineering discipline for AI coding agents. Loads discipline skills on demand and injects a discipline-check at session start so they actually fire — countering silent assumptions, sycophancy, overcomplication, scope creep, unverified 'done' claims, and insecure shortcuts.
★not rated 2 2mo agoA
tokens not measured
originalApache-2.0
Opsiyonel neon arayüz standardı + çok ajanlı iş rölesi. Kullanıcı ne istediğini söyler; iş büyüklüğü, ajan dağılımı, model ve denetim otomatik kurulur.
★not rated 2 6d agoA
tokens not measured
AGPL-3.0archived
Comment-concision mode. Shapes the code the model writes so comments earn their place (a non-obvious why, or meaning a name can't hold: config, units, constraints) and stay short. Hard one-line cap on inline comments, plus a density bar, so most functions carry none. Measurements, rejected alternatives, and the…
★not rated 2 1mo agoA
tokens not measured
originalMIT
Teach Claude your codebase, then keep it taught. On opt-in, clones registered git sources to a local cache (/.cache/skill-engine/) and installs per-skill context files under your project's .claude/skills/. Reads only paths you register.
★not rated 2
changed yesterdayA
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: