Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add heggria/taskflownpx agentmods add plugins/heggria/taskflow/marketplacegit clone --depth 1 https://github.com/heggria/taskflowGrade A, and why
taskflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "taskflow",
"metadata": {
"description": "Declarative, verifiable DAG orchestration for coding agents. Taskflow lets you define multi-phase subagent workflows (fan-out, gates, loops, tournaments, approvals, sub-flow composition) as JSON, verify them before they run, and keep intermediate transcripts out of your context — exposed to Codex, Claude Code, and OpenCode as the taskflow_* MCP tools plus a routing skill."
},
"owner": {
"name": "heggria",
"url": "https://github.com/heggria"
},
"plugins": [
{
"name": "taskflow",
"description": "Multi-phase subagent orchestration for Codex: 20 taskflow_* MCP tools (run/runs/resume/version/list/show/verify/compile/lint/plan/analytics/peek/trace/replay/why_stale/why_effect/recompute/reconcile_workspace/save/search) plus a routing skill. Background runs support status/wait/cancel; compile returns SVG + text outline. The server runs via npx (codex-taskflow).",
"source": "./packages/codex-taskflow/plugin",
"category": "developer-tools",
"homepage": "https://github.com/heggria/taskflow"
},
{
"name": "claude-taskflow",
"description": "Multi-phase subagent orchestration for Claude Code: 20 taskflow_* MCP tools (run/runs/resume/version/list/show/verify/compile/lint/plan/analytics/peek/trace/replay/why_stale/why_effect/recompute/reconcile_workspace/save/search) plus a routing skill. Background runs support status/wait/cancel; compile returns SVG + text outline. The server runs via npx (claude-taskflow).",
"source": "./packages/claude-taskflow/plugin",
"category": "developer-tools",
"homepage": "https://github.com/heggria/taskflow"
}
]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 27 lines scan A c214c57d979d
taskflow is a plugin published in the GitHub repository heggria/taskflow (67 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
wisp-local
Plugin marketplace listing 1 plugin: wisp.
wisp
Visual team-builder, plan-as-artifact, and live execution graph for autonomous Claude Code agent crews with WISP. Spawn a 3-role team, generate a DAG plan, run for hours, watch it ship in your browser.
connector-claude-code
Join the Cotal mesh — coordinate with other AI agents as lateral peers (presence, messaging, role requests) over NATS.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
claude-md-management-hames
Hames-aware fork of claude-md-management. Audits and revises CLAUDE.md files while honoring the v5.5 kernel + .cursor/rules/ module separation, workspace boundaries, defense-line signatures, and isolated domains.
vibe-flow
Orchestration skills for Vibe Kanban: plan → ship → link → review → merge with wave-based dispatch, executor routing (T0-T4), and autonomous fix loops.