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/MaxForAI/TokenlessWrote 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/maxforai/tokenless/claude-code)<a href="https://agentmods.dev/plugins/maxforai/tokenless/claude-code"><img src="https://agentmods.dev/badge/plugins/maxforai/tokenless/claude-code/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/maxforai/tokenless/claude-code"><img src="https://agentmods.dev/badge/plugins/maxforai/tokenless/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tokenless 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": "tokenless",
"version": "0.1.0",
"description": "Tokenless context compression for Claude Code. Cap noisy tool output locally before it enters model context.",
"license": "MIT",
"keywords": ["tokenless", "context", "compression", "agent", "claude-code", "hooks"],
"skills": "./skills",
"hooks": "./hooks/hooks.json"
}
What it installs
The manifest is a name and a version. 1 skill, 4 hooks travel with it, and installing the plugin installs all of them — 39 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 · 10 lines scan A ba6c0accd875
tokenless is a plugin published in the GitHub repository MaxForAI/Tokenless (46 stars, last pushed 5mo 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 2026-08-30.
Other plugins, from other repositories
rn-dev-agent
AI agent that fully tests React Native features on simulator/emulator — navigates the app, verifies UI, walks user flows, and confirms internal state.
ctk
Session continuity and context management toolkit - 11 skills, 1 agent, 12 commands, 31 shared hooks, session persistence, delta-cache token compression, web research, and smart context monitoring.
troth
Independent Substrate of Commitment — substrate IS the brain. Persistent identity across sessions, persistent memory and identity that survive across sessions and models, lability-window reconsolidation when contradicted, procedural reuse on recognized workflows. Open protocol (GMP v0.2), MCP-native, shared with the…
claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
wormhole
Collaborative AI memory layer - sync work between Claude Code, GitHub Copilot, and Cursor.
specclaw-review
Local review loop for specclaw: layered review rules, converging rounds, a bounded review memory behind an MCP server.