heggria /taskflow
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 122 tokens together
Declarative, verifiable DAG orchestration for Claude Code subagents — fan-out, gates, loops, tournaments, approvals, resumable runs, and saveable commands, with intermediate transcripts kept out of your context.
★ not rated 78 ▲
+2
changed 7d ago A
tokens not measured
original MIT heggria /taskflow
Agent Claude Code
Analyze requirements, ambiguity, and hidden constraints.
★ not rated 78 ▲
+2 yesterday A 11 tokens
original MIT heggria /taskflow
Agent Claude Code
Challenges planner and main-agent conclusions before risky decisions.
★ not rated 78 ▲
+2 yesterday A 11 tokens
original MIT heggria /taskflow
Agent Claude Code
Author and edit documentation FILES on disk (README, guides, changelogs, docs).
★ not rated 78 ▲
+2 yesterday A 23 tokens
original MIT heggria /taskflow
Agent Claude Code
Full-capability code executor for complex multi-file changes.
★ not rated 78 ▲
+2 yesterday A 13 tokens
original MIT heggria /taskflow
Agent Claude Code
Fast executor for scanning, command runs, summaries, and low-risk small edits.
★ not rated 78 ▲
+2 yesterday A 18 tokens
original MIT heggria /taskflow
Agent Claude Code
UI-focused executor for frontend component, layout, and styling changes.
★ not rated 78 ▲
+2 yesterday A 15 tokens
original MIT heggria /taskflow
Agent Claude Code
Implement planned code changes.
★ not rated 78 ▲
+2 yesterday A 6 tokens
original MIT heggria /taskflow
Agent Claude Code
Makes final decisions when multiple plans, critiques, or reviews conflict.
★ not rated 78 ▲
+2 yesterday A 17 tokens
original MIT heggria /taskflow
Agent Claude Code
Reviews and challenges implementation plans before execution on complex tasks.
★ not rated 78 ▲
+2 yesterday A 15 tokens
original MIT heggria /taskflow
Agent Claude Code
Creates concrete implementation plans, risk analysis, and acceptance criteria without editing files.
★ not rated 78 ▲
+2 yesterday A 16 tokens
original MIT heggria /taskflow
Agent Claude Code
Continue from a compact handoff — finds latest SESSIONSTATE.md and HANDOFF.md in .agent/, then acts on Next Actions.
★ not rated 78 ▲
+2 yesterday A 31 tokens
original MIT heggria /taskflow
Agent Claude Code
Reviews code, plans, architecture risk, and test gaps without editing files.
★ not rated 78 ▲
+2 yesterday A 17 tokens
original MIT heggria /taskflow
Agent Claude Code
Engineering risk review for backend, data, and infrastructure changes.
★ not rated 78 ▲
+2 yesterday A 15 tokens
original MIT heggria /taskflow
Agent Claude Code
Fast codebase recon that returns compressed context for handoff to other agents.
★ not rated 78 ▲
+2 yesterday A 17 tokens
copy · 86% MIT heggria /taskflow
Agent Claude Code
Review changes for security vulnerabilities and trust-boundary issues.
★ not rated 78 ▲
+2 yesterday A 14 tokens
original MIT heggria /taskflow
Agent Claude Code
Design and implement test strategy for a change.
★ not rated 78 ▲
+2 yesterday A 12 tokens
original MIT heggria /taskflow
Agent Claude Code
Runs validation commands, reproduces failures, and checks logs without editing files.
★ not rated 78 ▲
+2 yesterday A 17 tokens
original MIT heggria /taskflow
Agent Claude Code
Analyzes Figma design metadata, tokens, and specs from text-based context.
★ not rated 78 ▲
+2 yesterday A 19 tokens
original 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: