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 tmdry4530/code-flownpx agentmods add plugins/tmdry4530/code-flow/marketplacegit clone --depth 1 https://github.com/tmdry4530/code-flowGrade A, and why
code-flow 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- code-flow — 86% identical, 22 lines differ
What it actually says
{
"name": "code-flow",
"description": "code-flow — a dashboard that visualizes what your coding agent changed (timeline, diffs, architecture & data-flow graphs) with beginner-friendly explanations",
"owner": {
"name": "chamdom"
},
"plugins": [
{
"name": "code-flow",
"source": "./",
"description": "Visualize what your coding agent changed — timeline, diffs, architecture & data-flow graphs with beginner-friendly AI explanations",
"version": "0.1.0",
"license": "MIT",
"homepage": "https://github.com/tmdry4530/code-flow",
"author": {
"name": "chamdom",
"url": "https://github.com/tmdry4530"
}
}
]
}
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.
- yesterday First seen · 22 lines scan A a1ed7fd751d3
code-flow is a plugin published in the GitHub repository tmdry4530/code-flow (1 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 2026-08-31.
Other plugins, from other repositories
cwinvestments-memstack
MemStack™ — 130 battle-tested skills for Claude Code.
omen
Plugin marketplace listing 2 plugins: omen-development, omen-reporting.
codeweb
Plugin marketplace listing 1 plugin: codeweb.
webdev-agent-kit
Plugin marketplace listing 1 plugin: webdev-agent-kit.
loctree
CANONICAL loctree agent plugin (suite). Structural perception — slice before edit, impact before delete, find before create (incl. multi-literal OR A|B on MCP/LSP/CLI), prism before vc-polarize. Powered by loctree-mcp + loctree-lsp. Deprecated peer path: suite ./plugin/ (redirect only).
loctree-deprecated-redirect
DEPRECATED stub. Canonical Claude/Codex agent plugin is loctree-suite/loctree-plugin/. Do not install this path.