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 knitli/toolshednpx agentmods add plugins/knitli/toolshed/marketplacegit clone --depth 1 https://github.com/knitli/toolshedGrade A, and why
toolshed 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://catalog.lintel.tools/schemas/claude-code/marketplace/latest.json",
"name": "toolshed",
"owner": {
"name": "Knitli Inc.",
"email": "[email protected]"
},
"shared": {
"author": {
"name": "Knitli Inc.",
"email": "[email protected]"
},
"npmPrefix": "plugin-",
"npmScope": "knitli",
"repository": "https://github.com/knitli/toolshed",
"engines": {
"node": "catalog:"
},
"publishConfig": {
"access": "public",
"provenance": true,
"registry": "https://registry.npmjs.org/",
"tag": "latest"
},
"devEngines": {
"packageManager": {
"name": "bun",
"version": "catalog:",
"onFail": "download"
}
},
"homepage": "https://knitli.com",
"license": "MIT OR Apache-2.0",
"private": false,
"scopeAliases": {
"marketplace": ["mkt", "market", "mp"],
"codeweaver": ["cw"],
"decision-accountability": ["da", "decision"],
"strip-ansi": ["sa", "ansi"]
}
},
"metadata": {
"version": "1.0.0",
"description": "Knitli's agent plugin marketplace for Claude and other agents. Easily deploy Knitli tools like CodeWeaver, manage context, and keep your sessions clean and secure."
},
"plugins": [
{
"name": "ctx",
"source": "./plugins/ctx",
"description": "Context hygiene for AI-assisted codebases. Finds stale, contradictory, and drifting AI context files (CLAUDE.md, AGENTS.md, Serena memories, Cursor rules, and 10+ more tool ecosystems).",
"keywords": [
"context",
"memory",
"staleness",
"drift",
"hygiene",
"CLAUDE.md",
"AGENTS.md",
"multi-agent"
],
"category": "context-management",
"homepage": "https://knitli.com/ctx"
},
{
"name": "strip-ansi",
"source": "./plugins/strip-ansi",
"description": "Sanitizes ANSI escape sequences from tool output and detects terminal-basedWhat 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 · 143 lines scan A cdee38c04213
toolshed is a plugin published in the GitHub repository knitli/toolshed (1 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 2026-08-31.
Other plugins, from other repositories
motherduck-skills
Plugin marketplace listing 1 plugin: motherduck-skills.
motherduck-skills
MotherDuck skills for agents and developers: use the CLI and Guides, explore schemas, write DuckDB SQL, build Dives and Flights, and ship analytics apps and pipelines.
frappe-agent
Plugin marketplace listing 1 plugin: frappe-agent.
frappe-agent
Frappe, ERPNext, and Frappe ecosystem coding, customization, bench, and review intelligence for Claude Code and AI coding workflows.
supergraph
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
supergraph
Plugin marketplace listing 1 plugin: supergraph.