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 FlorianBruniaux/claude-code-pluginsnpx agentmods add plugins/florianbruniaux/claude-code-plugins/session-toolsgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/session-tools)<a href="https://agentmods.dev/plugins/florianbruniaux/claude-code-plugins/session-tools"><img src="https://agentmods.dev/badge/plugins/florianbruniaux/claude-code-plugins/session-tools.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
session-tools 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": "session-tools",
"description": "Session productivity — cost/token monitoring (ccboard), voice refinement, context catchup, MCP integration templates, and 11 session hooks",
"version": "1.0.0",
"author": { "name": "Florian Bruniaux" }
}
What it installs
The manifest is a name and a version. 8 skills, 6 commands, 1 agent, 1 plugin travel with it, and installing the plugin installs all of them — 514 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill mcp-integration-reference A 61 tokens
- Skill explain A 15 tokens
- Skill session-save A 31 tokens
- Skill catchup A 16 tokens
- Skill voice-refine A 46 tokens
- Skill handoff-create A 53 tokens
- Skill handoff-update A 60 tokens
- Skill handoff-resume A 40 tokens
- Command check-cache-bugs A 39 tokens
- Command autoresearch A 24 tokens
- Command session-save A 30 tokens
- Command catchup A 16 tokens
- Command routines-discover B 39 tokens
- Command diagnose D 10 tokens
- Agent loop-monitor A 34 tokens
- Plugin ccboard 7 inside A not measured
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 First seen · 7 lines scan A 3603bd685307
session-tools is a plugin published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d 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 2026-09-04.
Other plugins, from other repositories
pro-workflow
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 41 skills, 8 agents, 23 commands, 37 hook scripts across 24 events. Cross-agent via skills add.
badi
Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.
context-compress
Compress tool responses and keep explicitly indexed output searchable without flooding the agent context window.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
smartcompact
Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.
handoff
Portable project memory + development workflow for coding agents: auto-loads STATUS+RULES each session, enforces folder-level CONTEXT.md on edit, nudges durable state updates at turn end, scaffolds the system into any repo via guided discovery, and ships a tiered 6-phase workflow skill set covering every phase (brief.