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.
npx agentmods add skills/divadbaroon/claude-plugins/bart-skillnpx skills add divadbaroon/claude-plugins --skill bart-skillgit clone --depth 1 https://github.com/divadbaroon/claude-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.00316 |
| Opus 5 | $0.00006 | $0.00158 |
| Sonnet 5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
bart scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
When the hook runs, this text never reaches Claude: the command opens the goal workspace for this chat and ends the turn without a reply. You are reading it because the hook did not run — this session loaded its hook configuration before the plugin was installed or updated, and resuming a session keeps that configuration. So open the workspace yourself, the way the hook would:
"$HOME/.human-compact/bin/hc" chat-ui --session ${CLAUDE_SESSION_ID} --cwd "$(pwd)"
If that path does not exist, use hc chat-ui with the same arguments. The
command's last line is a http://127.0.0.1:PORT URL, which it opens in the
browser; a line above it beginning note: is for the reader too. A workspace
already open on older code than the plugin on disk is replaced rather than
reused, so the URL may differ from the one an earlier tab is on. Reply with
that URL, any note, and one sentence: the workspace is open, and a new Claude
Code session will open it without a reply. Nothing else: no other commands, no
files, no summary of the goals.
From this point the chat's goals document is injected as context on session
start, later messages, subagents and tool batches. /bart disable turns
that off for this chat.
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.
- 2d ago First seen · 27 lines · 12 tokens per session scan A 83a6b2d07f85
bart is a skill published in the GitHub repository divadbaroon/claude-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 316 once invoked, about $0.0001 per session on Opus 5. 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 skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.