Skip to content
>_ Awesome AI Skills
/

agentsys

by avifenesh

AI writes code. This automates everything else · 19 plugins, 47 agents, and 39 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

About

AI writes code. This automates everything else · 19 plugins, 47 agents, and 39 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

668
Stars
33
Skill Files
68
Forks
139
PRs Merged
6
Contributors
2
Issues Open
160
Issues Closed
2026-03-28
Last Activity
View on GitHub Stargazers Issues

Skill Analysis

238
Avg Lines / Skill
943
Avg Words / Skill
348
Code Blocks
386
Total Files
3.89 MB
Repo Size
0
Reference Files
Skill lines13 min / 256 median / 1024 max
Code languagesbash, javascript, json, markdown, regex, xml, yaml
Frontmatter keysallowed-tools, argument-hint, description, metadata, model, name, tools, version
Has CLAUDE.mdYes
Has LicenseYes
File typesjs (200), md (101), json (45), yml (9), ts (8), css (4), sh (3), html (2), toml (1), txt (1)

Skills (33)

  • maintain-cross-platform
    1024 lines3623 words54 blocks

    "Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's ...

    bashjavascriptjsonmarkdownregexyaml
  • test-agent
    13 lines27 words

    A test agent without role section

  • test-agent
    17 lines36 words

    A test agent with unrestricted bash

  • complete-agent
    25 lines86 words

    A fully complete and valid agent

  • enhance-prompts
    v5.1.0341 lines1187 words15 blocks

    "Use when improving general prompts for structure, examples, and constraints."

    bashjavascriptmarkdownxml
  • deslop
    v5.1.0205 lines718 words5 blocks

    "Use when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene."

    bashjavascript
  • discover-tasks
    v5.1.1298 lines1192 words19 blocks

    "Use when user asks to \"discover tasks\", \"find next task\", \"prioritize issues\", \"what should I work on\", or \"list open issues\". Discovers an...

    bashjavascriptmarkdown
  • web-auth
    v1.0.0178 lines933 words13 blocks

    "Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs for agent...

    bashjson
  • enhance-claude-memory
    v5.1.0388 lines1476 words15 blocks

    "Use when improving CLAUDE.md or AGENTS.md project memory files."

    markdown
  • validate-delivery
    v5.1.0187 lines572 words10 blocks

    "Use when user asks to \"validate delivery\", \"check readiness\", or \"verify completion\". Runs tests, build, and requirement checks with pass/fail ...

    bashjavascriptjson
  • perf-code-paths
    v5.1.033 lines106 words1 blocks

    "Use when mapping code paths, entrypoints, and likely hot files before profiling."

  • enhance-docs
    v5.1.0299 lines1105 words13 blocks

    "Use when improving documentation structure, accuracy, and RAG readiness."

    javascriptmarkdown
  • enhance-skills
    v5.1.0437 lines1458 words19 blocks

    "Use when reviewing SKILL.md files for structure and trigger quality."

    markdownyaml
  • enhance-plugins
    v5.1.0320 lines1092 words16 blocks

    "Use when analyzing plugin structures, MCP tools, and plugin security patterns."

    javascriptjsonmarkdownyaml
  • perf-benchmarker
    v5.1.052 lines160 words3 blocks

    "Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only ...

    javascript
  • debate
    v5.1.0317 lines1883 words8 blocks

    "Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress tes...

    json
  • perf-theory-gatherer
    v5.1.036 lines113 words1 blocks

    "Use when generating performance hypotheses backed by git history and code evidence."

  • perf-analyzer
    v5.1.038 lines105 words1 blocks

    "Use when synthesizing perf findings into evidence-backed recommendations and decisions."

  • enhance-orchestrator
    v5.1.0256 lines934 words9 blocks

    "Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report."

    javascriptmarkdown
  • repo-intel
    64 lines256 words2 blocks

    "Use when user asks to \"run repo intel\", \"generate repo map\", \"analyze repo\", \"query hotspots\", \"check ownership\", or \"bus factor\". Unifie...

    javascript

Recent Commits

-357 contributions across all repos
MarAprMayJunJulAugSepOctNovDecJanFebMar
Less
More
  • 94326af2026-03-28
    fix: flaky stale items test - use >= 99 for date boundary tolerance
    Avi Fenesh
  • 1cadfa02026-03-28
    5.8.1
    Avi Fenesh
  • 2eed4aa2026-03-28
    chore: bump repo-intel marketplace version to 0.2.0 (#322)
    Avi Fenesh
  • 9c694442026-03-28
    docs: sync agnix rule count 342 -> 385
    Avi Fenesh
  • 1bb431b2026-03-26
    feat(lib): add exports field to package.json for @agentsys/lib module resolution
    agent-cairn
  • 1dc88962026-03-26
    fix: use code-point safe truncate() across all text truncation sites
    avifenesh
  • 39822e72026-03-26
    fix: make truncate() code-point safe to prevent surrogate pair corruption
    avifenesh
  • 7087f222026-03-25
    fix: remove standalone How It Works section, fix test count
    Avi Fenesh
  • 2a1563e2026-03-25
    fix: agnix stats - 155 rules -> 342, 57 auto-fix -> 102, 28 categories -> 36
    Avi Fenesh
  • 62f27df2026-03-25
    feat: inline pipeline steps in each command panel
    Avi Fenesh