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/cdeust/session-optimizerWrote 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/cdeust/session-optimizer/refine-gate)<a href="https://agentmods.dev/plugins/cdeust/session-optimizer/refine-gate"><img src="https://agentmods.dev/badge/plugins/cdeust/session-optimizer/refine-gate/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/cdeust/session-optimizer/refine-gate"><img src="https://agentmods.dev/badge/plugins/cdeust/session-optimizer/refine-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
refine-gate 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 1mo 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": "refine-gate",
"description": "Prompt-binding gate for Claude Code: a UserPromptSubmit hook detects prompts carrying unbound references (\"the SSE solution\", \"like before\", \"still broken\") or ungrounded work requests, and injects the /refine procedure — build a binding table with evidence, separate symptom from goal, select an execution strategy from a research-backed table (15 strategies verified against 2024-2026 literature, counter-evidence included), and define acceptance criteria as external signals.",
"version": "2.1.0",
"author": {
"name": "Clement Deust",
"email": "[email protected]"
},
"homepage": "https://github.com/cdeust/session-optimizer",
"repository": "https://github.com/cdeust/session-optimizer",
"license": "MIT",
"keywords": [
"claude-code",
"prompt-engineering",
"refine",
"intent-binding",
"userpromptsubmit",
"execution-strategy"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 118 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.
- 1mo ago First seen · 21 lines scan A b93fefab54fb
refine-gate is a plugin published in the GitHub repository cdeust/session-optimizer (1 stars, last pushed 5d 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
cc-websearch
DDG-powered WebSearch and WebFetch replacement for Claude Code.
gearbox
Automatic model+effort routing for Claude Code: tiered subagents, escalation ladder, independent verifier, JSONL routing telemetry.
howl
Your AI screams — Howl listens. Blazing-fast Go statusline HUD with adaptive layouts and per-metric control.
super-bootstrap
Bootstrap or sync the development pipeline in any repo. /super-bootstrap:setup is a thin orchestrator: it installs/syncs the generic harness runway (CLAUDE.md, AGENTS.md foreign-executor contract, skeleton docs, path-scoped rules, the core plugin pin, default-on harness hooks (commit-channel routing raw commits to the.
claude-mini-hud
A lightweight Claude Code status bar that shows live details such as context, token use, balance, current tasks, tools, agents, cost, Git, estimated time, and warnings. It includes 21 display themes and has no runtime dependencies.
claude-brain
Sync and evolve your Claude Code brain across machines. Automatically exports, merges, and applies your accumulated knowledge (memory, skills, agents, rules, settings) across all your development machines via Git.