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 mopi1402/tayomi-cc-views --skill write-viewgit clone --depth 1 https://github.com/mopi1402/tayomi-cc-viewsWrote 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/mopi1402/tayomi-cc-views/write-view)<a href="https://agentmods.dev/skills/mopi1402/tayomi-cc-views/write-view"><img src="https://agentmods.dev/badge/skills/mopi1402/tayomi-cc-views/write-view.svg" alt="Measured on agentmods" 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 | $0.00115 | $0.01251 |
| Opus 5 | $0.00057 | $0.00626 |
| Sonnet 5 | $0.00023 | $0.00250 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
write-view 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a .view
A view is two halves that live apart: a TEMPLATE file dressing the data, and a BLOCK in the message carrying it. Get the halves confused and nothing draws.
Work in this order. Steps 1 and 5 are the ones that are skipped and the ones that cost the most.
1. Ask the engine what already exists
cc-views dict
It prints THIS install's own answer as JSON: every directive with what it takes, every tag name, and
every view the search path resolves, in resolution order, each with the fields it spends and the
payload it expects. Read it before writing anything.
A view whose spends already covers the fields you have is a view you do not have to write. The
bundled ones cover most asks: banner and quote over a markdown quote, columns and lines over a
markdown table, box over a table whose header row is a title and a badge rather than column names,
mermaid over an ordinary ```mermaid fence (its ONLY payload, drawn in the terminal), hr on its
own line. If one fits, go straight to step 4 and write no file at all. One view, one payload shape:
the payload field in cc-views dict names the single form each one accepts, and any other shape
under its decorator shows raw.
2. Read the language, never infer it
The generated reference ships inside the package, dumped from the tables the engine executes:
node_modules/@tayomi/cc-views/agent/catalogue.json
Every directive with what it takes, what it opens and what closes it, the containers each is read in, the two carriers and the data block's line forms, every tag name with the suffixes a colour derives, and every view this package ships. It cannot drift from the engine: a word taken out of the table stops being read, and the render changes with it.
Beside it, docs/CHEATSHEET.md is the same language written for a human, and carries the worked
example the JSON has no room for. Read one of the two rather than guessing a directive that reads
plausibly, and read one of the two rather than trusting this file, which teaches the PROCEDURE and
not the grammar.
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.
- 8d ago First seen · 114 lines · 115 tokens per session scan A 863ddd8c6d2d
write-view is a skill published in the GitHub repository mopi1402/tayomi-cc-views (3 stars, last pushed 22d ago), licensed MIT. It adds 115 tokens to every session and 1,251 once invoked, about $0.0006 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
release
Automated release management - version updates, changelog generation, git tagging, and GitHub release creation.
hooks-daemon
Manage Claude Code Hooks Daemon - install, upgrade, check health, restart, and develop project-level handlers.
configure
View and modify hooks daemon handler configuration - enable/disable handlers, change priorities, set handler options.
mode
Get or set daemon operating mode - switch between default and unattended (blocks Stop events).
docs-qa
Audit this project's documentation for SSoT violations — conflicting truths, duplicated facts, stale pointers, and verbose comment blocks acting as documentation. Trigger on requests like "audit the docs", "check for conflicting truths", "docs drift", "is this documentation duplicated anywhere".
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…