Agent
Part of bootstrap
Generates complete agent prompt files using LLM expertise (no templates!).
4,274 tagged developer-tools, measured the same way as everything else here.
Browse within: code-quality 123gemini-cli 114Code Generation 110hooks 106spec-driven-development 71ai-assistant 68agentic 63agentic-workflow 58gemini 56prompt-engineering 53ai-workflow 52opencode 52workflow 49claude-code-plugins 45
Agent
Part of bootstrap
Generates complete agent prompt files using LLM expertise (no templates!).
Agent
Decide canonical/duplicate/related/unrelated outcomes for issue and PR clusters.
Agent
Discover additional similar issues and PRs from GitHub before final dedupe decisions.
Agent
Merge sub-agent findings into operator-ready output for dedupe execution.
Agent
Creates, amends, and supersedes standalone MADR ADR files under specs/adrs/ and prepares sad.md ADR catalog updates.
Agent
Detects the current feature branch, derives the feature directory, validates prerequisites, and returns structured context for other SDD Pilot agents.
Agent
QC sub-agent. Executes tests, static analysis, and security tools. Asks user for permission before installing missing dependencies.
Agent Claude Code
Review code for quality, architectural consistency, and integration issues. Use after implementing features, refactoring, or before merging PRs.
Agent Claude Code
Execute a development plan created by the plan agent — spawn parallel subagents per phase, test, and ship.
Agent Claude Code
Triage, analyze, and create phased development plans. Iterate with the user until the plan is approved.
Agent
Part of ai-sdlc
CI-triggered PR conflict-resolver. Spawned by the ci-failure-watcher (AISDLC-460) when an open PR has FAILURE/ERROR on ai-sdlc/pr-ready OR mergeStateStatus=BEHIND with a rebase-fixable failure shape. Reuses the rebase-resolver flow — rebases onto origin/main, resolves mechanical conflicts (test additions, prettier…
Agent
Part of ai-sdlc
Delegates code review to Codex CLI and returns the same JSON envelope as code-reviewer, enabling cross-harness review workflows.
Agent
Part of ai-sdlc
Implements backlog tasks against the spec, runs verification, commits work.
GantisStorm/essentials-claude-code
Agent
Verbatim plan-to-beads converter using the bd CLI. Copies full implementation code, requirements, and exit criteria directly into each bead. Each bead is 100% self-contained - no plan back-references or external lookups needed.
GantisStorm/essentials-claude-code
Agent
Architectural Bug Investigation Agent. Deep investigation with line-by-line code analysis, produces fix plans with exact code changes, regression prevention, and verification criteria. Plans work with any executor (loop or swarm).
GantisStorm/essentials-claude-code
Agent
Architectural Code Quality Agent (LSP-Powered) - Creates comprehensive architectural improvement plans suitable for loop or swarm executors (/implement-loop, /tasks-loop or /tasks-swarm, /beads-loop or /beads-swarm). Uses Claude Code's built-in LSP for semantic code understanding. This agent thoroughly analyzes code…
Agent
Part of agi-super-team
Use this portable startup order inside an installed workspace.
Agent
Part of agi-super-team
A complete roster of the AGI Super Team C-Suite agents.
Agent
Part of agi-super-team
This workflow is copied into every generic role workspace. A harness supplies models, tools, delegation, and scheduling; none of those capabilities are assumed to exist.
Agent
Part of godot-devtool
Builds, edits, runs, debugs, and verifies Godot 4 projects through the godot-devtool MCP server.
Agent
PROACTIVELY use this agent when developing or debugging mini-agents, understanding agent patterns, or troubleshooting MCP integrations. Read-only agent for production safety.
Agent
PROACTIVELY use when main Claude needs context before proceeding. Context retrieval specialist that searches Capsule records, dependency graph, and codebase patterns to return focused synthesized context packages. Use when: uncertain about context, before reading files, before spawning specialists, when user mentions…
Agent
Use this agent for git workflow guidance, branching strategies, merge conflict resolution, and git best practices. Helps with complex git operations and maintaining clean git history.
alfredoperez/speckit-companion
Agent
Generate a custom checklist for the current feature based on user requirements.
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: