pm
49Agent
Feature planning and dependency management. Use before writing new feature code.
not rated 2 3mo ago A 0 tokens
original MIT
reviewer
50Agent
Review changes before commit/PR for quality, security, tests. Auto-fix safe issues; escalate the rest.
not rated 2 3mo ago A 0 tokens
original MIT
Coder
51Agent
Execute implementation instructions delegated by agent mode. Use for coding tasks that need file edits, shell commands, and verification.
not rated 2 4d ago A 25 tokens
original MIT
Agent
Explore intent, requirements, and design before implementation. Use for new features, creative work, and design-first sessions.
not rated 2 4d ago A 23 tokens
original MIT
writing
53Agent
Rewrite, translate, polish, and structure text with natural voice. Use for copy editing, messages, docs tone, and English correction.
not rated 2 4d ago A 27 tokens
original MIT
evaluator
54Agent Claude Code
Grades work against the plan's acceptance criteria from a separate context window. Use in the evaluate stage. The anti-self-praise firewall — must never be the agent that built the work. Verifies by running tests/app, returns pass/fail per criterion with evidence.
not rated 2 23d ago A 56 tokens
original MIT
explorer
55Agent Claude Code
Disposable read-only fan-out. Use whenever a task needs broad searching or large-file reading that would blow the caller's 40% budget. Burns its own context, returns a short distillate, and dies. The context firewall — keeps the caller in the smart zone.
not rated 2 23d ago A 58 tokens
original MIT
gardener
56Agent Claude Code
Entropy garbage-collector. Use periodically/in background to scan for drift — stale docs, dead always-loaded context, code smells, convention drift — and open small, green, one-move fixes. Keeps the repo coherent and the smart zone smart for future runs.
not rated 2 23d ago A 55 tokens
original MIT
Agent
Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.
not rated 50 11d ago A 64 tokens
MIT
Agent
DC-based PPA optimization RTL patcher. Reads ppa-report.json + RTL + requirements.json, emits RTL unified diff + rationale + DC Tcl snippet. Timing-first heuristic. Never modifies files outside allowededitscope.
not rated 50 11d ago A 49 tokens
MIT
Agent
AXI/AHB/APB protocol verification specialist. Writes protocol-specific SVA assertions and validates handshake timing compliance.
not rated 50 11d ago A 26 tokens
MIT
Agent
Reviews a trusted code workspace for correctness, security, regressions, and missing tests.
not rated 47 today A 20 tokens
MIT
Agent
Troubleshoots Everruns Framework and Platform questions using public documentation and structured investigation notes.
not rated 47 today A 22 tokens
MIT
Agent
Coordinates a production incident with an evidence log, bounded actions, and stakeholder updates.
not rated 47 today A 19 tokens
MIT
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: