Skip to content

everything-claude-code

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

About

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

259,232
Stars
1293
Skill Files
38,778
Forks
1052
PRs Merged
359
Contributors
66
Issues Open
708
Issues Closed
2026-09-12
Last Activity

Skill Analysis

226
Avg Lines / Skill
805
Avg Words / Skill
9363
Code Blocks
3715
Total Files
51.23 MB
Repo Size
72
Reference Files
Skill lines12 min / 159 median / 960 max
Code languagesbash, batch, blade, caddyfile, cmake, cpp, csharp, css, dart, diff, django, dockerfile, erb, fsharp, gitignore, go, html, ini, iss, java, javascript, json, jsonl, kotlin, lua, markdown, md, mermaid, no_run, perl, php, powershell, prisma, properties, python, ruby, rust, sh, solidity, sql, swift, text, toml, ts, tsx, typescript, vue, xml, yaml
Frontmatter keysabout, allowed-tools, allowedTools, argument-hint, assignees, author, category, color, command, description, homepage, inclusion, labels, license, metadata, model, name, origin, repo, run_mode, tags, title, tools, version
Has CLAUDE.mdYes
Has LicenseYes
File typesmd (2527), js (600), py (146), json (137), yaml (49), sh (34), png (34), txt (30), yml (20), ts (19)

Skills (1291)

  • network-architect
    107 lines658 words1 blocks

    Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, an...

    text
  • mle-reviewer
    163 lines1402 words3 blocks

    Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model ser...

    bashtext
  • marketing-agent
    160 lines1105 words1 blocks

    Marketing strategist and copywriter for campaign planning, audience research, positioning, copy creation, and content review. Covers landing pages, em...

    text
  • opensource-sanitizer
    198 lines907 words7 blocks

    Verify an open-source fork is fully sanitized before release. Scans for leaked secrets, PII, internal references, and dangerous files using 20+ regex ...

    bashmarkdown
  • loop-operator
    46 lines274 words

    Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.

  • gan-evaluator
    233 lines1296 words9 blocks

    "GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Gene...

    bashmarkdown
  • security-reviewer
    118 lines780 words1 blocks

    Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints...

    bash
  • build-error-resolver
    124 lines736 words2 blocks

    Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal dif...

    bash
  • typescript-reviewer
    125 lines1253 words1 blocks

    Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all Type...

    bash
  • code-simplifier
    57 lines318 words

    Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed...

  • refactor-cleaner
    95 lines548 words1 blocks

    Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depc...

    bash
  • gan-generator
    141 lines871 words3 blocks

    "GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met."

    markdown
  • kotlin-reviewer
    169 lines1066 words4 blocks

    Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violati...

    kotlin
  • python-reviewer
    108 lines630 words2 blocks

    Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes....

    bashtext
  • java-reviewer
    191 lines1702 words2 blocks

    Expert Java code reviewer for Spring Boot and Quarkus projects. Automatically detects the framework and applies the appropriate review rules. Covers l...

    bash
  • java-build-resolver
    276 lines1700 words10 blocks

    Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-s...

    bashtext
  • harness-optimizer
    56 lines672 words

    Improve local agent-harness configuration reliability and cost using eval-driven grading (pass@k/pass^k) derived from the eval-harness skill.

  • agent-evaluator
    207 lines1113 words3 blocks

    Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness). Use after any non-trivial task whe...

  • vue-reviewer
    207 lines2076 words3 blocks

    Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-speci...

    bash
  • conversation-analyzer
    62 lines346 words1 blocks

    Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.

    yaml

Recent Commits

-370 contributions across all repos
SepOctNovDecJanFebMarAprMayJunJulAugSep
Less
More
  • 83210212026-09-12
    fix(memory): classify directory traversal failures
    Affaan Mustafa
  • 90ef62c2026-09-12
    fix(memory): distinguish incomplete reads from missing records
    Affaan Mustafa
  • b6ddd132026-09-12
    Fix/rails patterns followups
    Rockwell Windsor Rice
  • ab1f1a02026-09-12
    feat: group verified capsules into offline retrospective reports
    Affaan Mustafa
  • 1ed03ec2026-09-12
    feat(control-pane): live control-plane view with 2D projection and static-threshold advisories
    Affaan Mustafa
  • 1ac07902026-09-12
    fix(hooks): keep hooks.json within Claude Code's schema
    zpearce-2814
  • c4904e32026-09-12
    fix(catalog): remove Serply and Squish entries (#3094)
    Affaan Mustafa
  • fba8e352026-09-12
    feat(mcp): add serply-search server catalog entry (#3085)
    Serply
  • bdf92d82026-09-12
    docs: add explicit hook consent to OpenCode install command (#3080)
    Radosław Kaznowski
  • 4f373872026-09-12
    fix(hooks): block-no-verify handles stuck optional values and long-option prefixes (#3073)
    Zaal