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/liorwn/claudetopWrote 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/commands/liorwn/claudetop/usage)<a href="https://agentmods.dev/commands/liorwn/claudetop/usage"><img src="https://agentmods.dev/badge/commands/liorwn/claudetop/usage/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/commands/liorwn/claudetop/usage"><img src="https://agentmods.dev/badge/commands/liorwn/claudetop/usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00034 | $0.00170 |
| Opus 5 | $0.00017 | $0.00085 |
| Sonnet 5 | $0.00007 | $0.00034 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
claudetop-usage
Show how much of each Claude.ai plan window is used and how much is left, with reset times.
If --refresh is passed, force a refetch first; otherwise the cached numbers (refreshed at most every 60s by the status line) are shown.
if [ "$ARGUMENTS" = "--refresh" ]; then claudetop-usage --refresh; fi
claudetop-usage --show
Run the command and display the full formatted output to the user. Do not summarize.
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.
- yesterday First seen · 20 lines · 34 tokens per session scan A 345d393becee
usage is a command published in the GitHub repository liorwn/claudetop (213 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 170 once invoked, about $0.0002 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 2026-09-08.
Other commands, from other repositories
skene-build
Build an implementation prompt for the selected growth loop. Generates context-aware instructions with code examples and testing checklists.
skene-deploy
Deploy telemetry upstream after build. Expects skene-context/engine.yaml, skene-context/feature-registry.json (or configured outputdir; legacy skene/feature-registry.json still works), and supabase/migrations/skenetriggers.sql; push uploads the package to Skene Cloud.
skene-init
Initialize Skene configuration for this project. Creates .skene.config (TOML), sets up provider and API key (or SKENEAPIKEY), and runs validation.
skene-status
Check implementation status from skene-context/engine.yaml. Validates features, action vs code-only mode, and that trigger/function SQL exists in migrations; detail shows latest matching file and (+N) if duplicates.
skene-analyze
Analyze current codebase for PLG opportunities. Scans tech stack, detects existing growth features, identifies revenue leakage, and updates the feature registry.
skene-plan
Generate a prioritized growth loop implementation plan. Creates a list of growth loops ranked by impact and effort, with estimated implementation time.