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 dtormoen/tsk-tsknpx agentmods add plugins/dtormoen/tsk-tsk/tsk-helpgit clone --depth 1 https://github.com/dtormoen/tsk-tskGrade A, and why
tsk-help 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": "tsk-help",
"description": "Teaches Claude core tsk commands for delegating development tasks to AI agents in sandboxed containers.",
"author": {
"name": "tsk-tsk contributors"
}
}
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 · 8 lines scan A ee6b31203052
tsk-help is a plugin published in the GitHub repository dtormoen/tsk-tsk (170 stars, last pushed 1mo 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
cq
Shared knowledge commons for AI agents; find, share, and confirm collective knowledge to stop rediscovering the same failures.
knowledge
Knowledge management commands and hooks for extracting learnings from Claude Code sessions.
dinf
D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, as a working toolchain: an agent embodied in a directory, three operators (FACTOR / ADJOIN / CHRISTEN), and a gate that catches a missing closure at the syntax level.
ping-identity
Agent plugins for Ping Identity — teach any AI coding agent how to build with Ping Identity.
learning-agents
Auto-improving AI sub-agents that learn from their mistakes across sessions.
simple-agent-memory
Plugin marketplace listing 1 plugin: simple-agent-memory.