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/jongwony/epistemic-protocolsWrote 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/jongwony/epistemic-protocols/route)<a href="https://agentmods.dev/plugins/jongwony/epistemic-protocols/route"><img src="https://agentmods.dev/badge/plugins/jongwony/epistemic-protocols/route.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
route 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": "route",
"description": "Route the accumulated session context to the core protocol whose deficit it shows — /route (a per-prompt hook directive triggers it)",
"version": "0.10.0",
"author": {
"name": "Jongwon Choi",
"url": "https://github.com/jongwony"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 42 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 Changed bf1367a88c9d
- yesterday Changed c7cff8dbc96a
- 2d ago Changed 646731a32943
- 3d ago First seen · 10 lines scan A 5adc7dcd5b41
route is a plugin published in the GitHub repository jongwony/epistemic-protocols (160 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 2026-09-03.
Other plugins, from other repositories
workflow
Session workflow helpers and deferred-work backlog - knowledge capture, confusion handling, course correction, clipboard copy, backlog items.
recall
Cross-session, cross-project conversation recall: verbatim exchanges and the commands Claude ran, ranked search with match snippets, secrets redacted at index time, compaction recovery, highlight sharing, and a skill Claude invokes on its own.
yaps-dictation
Voice-type into Claude Code and other desktop apps through Yaps.
cc-hud
Compact statusline HUD for Claude Code — context, agents, rate limits.
career-cc
Template for an AI-native job-search workflow built with Claude Code. Skills for resume customization, JD evaluation, interview prep, outreach, salary negotiation, and application tracking. Clone into a private repo and personalize.
claude-statusline
Zero-dependency statusline for Claude Code with rainbow progress bar, 10 themes, rate limit monitoring, and natural language configuration.