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 keshrath/agent-tasksnpx agentmods add plugins/keshrath/agent-tasks/marketplacegit clone --depth 1 https://github.com/keshrath/agent-tasksGrade A, and why
agent-tasks 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 2d ago.
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": "agent-tasks",
"owner": {
"name": "keshrath"
},
"metadata": {
"description": "Pipeline-driven task management for AI coding agents.",
"version": "1.0.0"
},
"plugins": [
{
"name": "agent-tasks",
"source": "./",
"description": "Pipeline-driven task management for AI coding agents. Tasks flow through backlog → spec → plan → implement → test → review → done stages with dependencies, per-stage artifacts, multi-agent claiming, and a live Kanban dashboard on :3422.",
"category": "workflow",
"tags": ["mcp", "tasks", "pipeline", "kanban"]
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 20 lines scan A 6cd7356a7d89
agent-tasks is a plugin published in the GitHub repository keshrath/agent-tasks (15 stars, last pushed 4mo 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
flux
Plugin marketplace listing 1 plugin: flux.
scrumboy-board-operator
Agent plugin with Skills for operating Scrumboy boards through its MCP and Agoragentic APIs.
ai-agents-skills
Skills + hooks for Claude Code: teamlead (main thread as team-lead: delegate code work to subagents, surface only decisions), roadmap (plan & autonomously build a whole app phase-by-phase), kanban (manage a .claude/kanban board), schedule-tasks (auto-pilot todo cards via at/tmux), git-flow (shared git core: commits.
ticket-flow
Kanban- or beads-backed git-worktree ticket workflow plugin for Claude Code.
ticket-flow
Beads-backed ticket workflow for Claude Code: spec → pickup → implement → finish behind verdict and merge gates, orchestrated by /flow (--local with resume, --parallel, --serial/--loop unattended queue runner), each ticket in its own git worktree. Five visible commands; the phase skills are model-invoked.
trello
A pack of Trello skills for Claude Code and Codex - manage boards, lists and cards; sort a shopping list into store-aisle order; generate a board status digest; see what is due across boards; and set up and run a personal board that actually gets things done. Via the Trello REST API.