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/codeshux/tokenwise/summarynpx skills add CodeShuX/tokenwise --skill summarygit clone --depth 1 https://github.com/CodeShuX/tokenwiseWhat 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 | $0.00059 | $0.00724 |
| Opus 5 | $0.00030 | $0.00362 |
| Sonnet 5 | $0.00012 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
summary 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.
This is a copy
91% identical to CodeShuX__tokenwise — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tokenwise:summary — Multi-session trend report
Aggregate .tokenwise/log.ndjson over a time window.
Parse $ARGUMENTS
--week(default) — last 7 days--month— last 30 days--all— entire log--days <N>— last N days--out <path>— write the report to a markdown file instead of stdout--json— output JSON instead of text
Steps
-
Read
./.tokenwise/log.ndjson(or the path the user provides) -
Filter entries to the time window:
- Compute cutoff:
now - <days>*86400 - Keep entries where
ts > cutoff
- Compute cutoff:
-
Aggregate:
- Total: sessions (unique session_id), tasks, total cost, baseline cost, savings
- Per model: task count, cost, % of total
- Per task_class (
mechanical|execution|review|planning): task count, avg cost, dominant model - Trend (only for
--weekor--days <≤14>): per-day cost + savings bar chart in plain text
-
Print:
TokenWise Summary — last <N> days
==================================
Sessions: <count>
Tasks routed: <count>
Total spent: $<total>
Baseline: $<baseline>
Savings: $<savings> (<pct>%)
Per model:
Haiku <count> tasks $<cost> (<pct>%)
Sonnet <count> tasks $<cost> (<pct>%)
Opus <count> tasks $<cost> (<pct>%)
Fable <count> tasks $<cost> (<pct>%)
Top task classes:
<class> <count> tasks avg cost $<avg> model: <dominant>
...
Daily trend (cost):
Mon ███████░░░ $4.21
Tue ███░░░░░░░ $1.82
Wed ████████░░ $5.04
...
-
If
--out <path>was provided, write the markdown version of the report to that path. Use a proper markdown table for the trend section. -
If
--json, dump the aggregated data structure as pretty-printed JSON.
Notes on small log files
- If <2 sessions in the window: print the report but add
Note: too few sessions for meaningful trend data. - If log file is empty/missing: print the same "No TokenWise log found" message that
/tokenwise:reportuses. - Omit any "Per model" row whose count is 0 for the window — Fable's row will legitimately be absent for most users most of the time.
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 · 74 lines · 0 tokens per session scan A 593be973f66e
summary is a skill published in the GitHub repository CodeShuX/tokenwise (3 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 724 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to CodeShuX__tokenwise, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
學習使用者的 Facebook/Instagram/YouTube/Threads/X 語氣與受眾,規劃、撰寫、確認後發佈內容;以已登入 Chrome 受控掃描、草擬及回覆 FB/IG/Threads 留言;並作為流量、留存與轉化的結構化帳本。使用者說「發文」「用我的口氣」「回覆留言」「自動回留言」「掃留言」「查流量」「演算法」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。.
privacy-jp
日本サービス向け(일본 서비스용) プライバシーポリシー・利用規約・同意モーダル・Cookieバナー 자동 생성. 個人情報保護法(APPI)·消費者契約法·特定商取引法 반영. Next.js 1316 프로젝트 대상.
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…
higgsfield-camera
Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.