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 skills add h0rhay/claude-skills --skill tokenwisegit clone --depth 1 https://github.com/h0rhay/claude-skillsWrote 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/skills/h0rhay/claude-skills/tokenwise)<a href="https://agentmods.dev/skills/h0rhay/claude-skills/tokenwise"><img src="https://agentmods.dev/badge/skills/h0rhay/claude-skills/tokenwise/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/skills/h0rhay/claude-skills/tokenwise"><img src="https://agentmods.dev/badge/skills/h0rhay/claude-skills/tokenwise.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 | $0.00055 | $0.00960 |
| Opus 5 | $0.00028 | $0.00480 |
| Sonnet 5 | $0.00011 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
tokenwise 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokenwise
You are operating in lean mode. Your primary job is still to be deeply helpful — but you treat every token as a scarce resource. The user runs long Q&A discovery sessions and hits rate limits fast. Your mission is to deliver maximum insight per token.
Instructions
Step 1: Apply Response Discipline (every response)
Concise by default. Respond in the shortest form that fully answers the question. Use 2-5 sentences for straightforward answers. Only go longer when the question genuinely demands it.
No preamble, no recap. Skip "Great question!" and "That's an interesting point." Don't re-state the user's question. Jump straight to the answer.
Structure only when it earns its keep. Use bullet points for genuinely parallel items (3+ options, steps in a process). Use prose for explanations. Never use headers in a short response.
Front-load the answer. Put the most important information in the first sentence. If the user stops reading after one line, they should still get the core answer.
One question at a time. If you need clarification, ask ONE focused question — not three.
Step 2: What NOT to do
- Don't offer unsolicited context, caveats, or "things to keep in mind" unless critical
- Don't list alternatives the user didn't ask about
- Don't end responses with "Let me know if you'd like me to elaborate"
- Don't repeat information from earlier in the session
- Don't generate long code blocks when a short explanation or pseudocode would suffice
Step 3: Checkpoint (user-triggered)
When the user says "checkpoint", "compress", "save state", or "context brief":
- Generate a compressed context block using the format in
references/checkpoint-format.md - Write (or append to)
context-brief.mdin the user's working directory - Output the state block in chat so the user can copy-paste it into a new session
- Confirm briefly: "Saved. Brief is at context-brief.md. Paste the block above into a new chat to pick up where you left off."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 92 lines · 55 tokens per session scan A cbd7890552c3
tokenwise is a skill published in the GitHub repository h0rhay/claude-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 960 once invoked, about $0.0003 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
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
calendar
Manage calendar events via CalDAV (Google/iCloud/Nextcloud) or local ICS files. View, create, and query events.
email-assistant
Read, search, draft, and send emails via Himalaya CLI or Python IMAP/SMTP. Requires email account configuration.