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.
git clone --depth 1 https://github.com/aj604/toolshedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/aj604/toolshed/workbench)<a href="https://agentmods.dev/plugins/aj604/toolshed/workbench"><img src="https://agentmods.dev/badge/plugins/aj604/toolshed/workbench/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/aj604/toolshed/workbench"><img src="https://agentmods.dev/badge/plugins/aj604/toolshed/workbench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
workbench 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 today.
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": "workbench",
"version": "0.1.0",
"description": "An SDLC toolkit for Claude Code. Ships orchestrate-issues: drive a GitHub issue dependency graph to completion with background agents (implementer, spec reviewer, fixer and more), one worktree and one reviewed PR per issue.",
"license": "MIT",
"homepage": "https://github.com/aj604/toolshed",
"repository": "https://github.com/aj604/toolshed",
"keywords": [
"sdlc",
"github",
"issues",
"orchestration",
"subagents",
"worktrees",
"code-review"
],
"author": {
"name": "Avery Jones",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill, 7 agents travel with it, and installing the plugin installs all of them — 614 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today First seen · 22 lines scan A c2d7ba433e16
workbench is a plugin published in the GitHub repository aj604/toolshed (1 stars, last pushed today), 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 2026-10-19.
Other plugins, from other repositories
model-apps
Build model-driven Power Apps end to end: /app-builder authors whole apps (tables, relationships, forms, views, charts, security roles, app + sitemap) from a natural-language intent, and /genpage builds generative pages with specialist agents for planning, entity creation, and parallel code generation. Requires PAC…
power-automate
Build, edit, run, and debug Power Automate cloud flows via the FlowAgent MCP server — connection lifecycle, surgical edits, copy across environments, run management, and validated expressions.
team-motivation
Team motivation and management skills including Daniel Pink's Autonomy, Mastery, Purpose (AMP) principles and Andy Grove's High Output Management (leverage, one-on-ones, OKRs, task-relevant maturity).
catchup
Async-team return-from-absence briefing. /catchup fans out to GitHub, git, Linear, and calendar, then emits one prioritized Context Brief instead of a firehose.
arrow-maintenance
Scaling layer for linked-intent-dev. Tracks spec-to-code coherence across large projects via docs/arrows/ index. Includes brownfield bootstrap for mapping existing codebases.
recursive-decomposition
Decompose dense codebase-wide, multi-document, and large-PDF work even when it fits the window. Depth-1 sub-agents, then verify. Based on Recursive Language Models (Zhang, Kraska, Khattab, arXiv:2512.24601).