Skip to content

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.

986
Stars
31
Skill Files
115
Forks
189
PRs Merged
8
Contributors
0
Issues Open
170
Issues Closed
2026-09-13
Last Activity

Skill Analysis

231
Avg Lines / Skill
878
Avg Words / Skill
292
Code Blocks
406
Total Files
4.14 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 (222), md (99), json (45), yml (10), ts (8), css (4), html (2), toml (1), txt (1), png (1)

Skills (31)

  • perf-investigation-logger
    v5.1.042 lines94 words1 blocks

    "Use when appending structured perf investigation notes and evidence."

  • perf-theory-tester
    v5.1.037 lines98 words1 blocks

    "Use when running controlled perf experiments to validate hypotheses."

  • enhance-hooks
    v5.1.0555 lines1862 words22 blocks

    "Use when reviewing hooks for safety, timeouts, and correct frontmatter."

    bashjavascriptjsonmarkdownyaml
  • perf-baseline-manager
    v5.1.031 lines85 words1 blocks

    "Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version."

  • 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
  • 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
  • enhance-agent-prompts
    v5.1.0278 lines971 words17 blocks

    "Use when improving agent prompts, frontmatter, and tool restrictions."

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

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

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

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

    markdown
  • perf-profiler
    v5.1.042 lines120 words2 blocks

    "Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence."

    javascript
  • enhance-cross-file
    v5.1.0111 lines473 words4 blocks

    "Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions."

    bashjavascriptmarkdownyaml
  • 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
  • learn
    v5.1.0349 lines1107 words12 blocks

    "Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build knowledg...

    javascriptjsonmarkdown
  • orchestrate-review
    v5.1.0261 lines1146 words7 blocks

    "Use when user asks to \"deep review the code\", \"thorough code review\", \"multi-pass review\", or when orchestrating the Phase 9 review loop. Provi...

    javascriptjson
  • consult
    v5.1.0426 lines2733 words12 blocks

    "Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult another AI...

    bashjson
  • drift-analysis
    v5.1.0325 lines1094 words10 blocks

    Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or nee...

    javascriptjsonmarkdownyaml
  • discover-tasks
    v5.1.1298 lines1195 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
  • enhance-plugins
    v5.1.0320 lines1092 words16 blocks

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

    javascriptjsonmarkdownyaml
  • enhance-skills
    v5.1.0437 lines1458 words19 blocks

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

    markdownyaml
  • 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

Recent Commits

-327 contributions across all repos
SepOctNovDecJanFebMarAprMayJunJulAugSep
Less
More
  • dc49e042026-09-13
    chore(deps-dev): bump jest in the security-and-patches group (#399)
    dependabot[bot]
  • f65feb62026-09-05
    chore(deps-dev): bump jest in the security-and-patches group (#397)
    dependabot[bot]
  • 77c897e2026-08-27
    docs: add inference.tiyuvta.ai banner for always-on agent users
    Avi Fenesh
  • 846ee282026-08-25
    Merge pull request #396 from agent-sh/chore/release-6.0.2
    Avi Fenesh
  • 2b7eab62026-08-17
    chore: release v6.0.2
    Avi Fenesh
  • a0b2c8d2026-08-17
    fix(adapters): delete the two install.sh scripts instead of documenting them (#395)
    Avi Fenesh
  • 471c11b2026-08-16
    fix(windows): resolve dev-install's claude through where.exe, not a fixed suffix (#394)
    Avi Fenesh
  • 39e44f52026-08-16
    fix(windows): run dev-install's external commands without a shell (#393)
    Avi Fenesh
  • ff005f92026-08-16
    ci: run the test job on windows-latest too (#392)
    Avi Fenesh
  • 5b46d8e2026-08-16
    fix(windows): route .cmd shims through cmd.exe at every spawn site (#391)
    Avi Fenesh