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 elct9620/claudekit --skill concise-docsgit clone --depth 1 https://github.com/elct9620/claudekitWrote 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/elct9620/claudekit/concise-docs)<a href="https://agentmods.dev/skills/elct9620/claudekit/concise-docs"><img src="https://agentmods.dev/badge/skills/elct9620/claudekit/concise-docs/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/elct9620/claudekit/concise-docs"><img src="https://agentmods.dev/badge/skills/elct9620/claudekit/concise-docs.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 | $0.00120 | $0.02073 |
| Opus 5.5 | $0.00048 | $0.00829 |
| Sonnet 5.5 | $0.00024 | $0.00415 |
| Haiku 4.5 | $0.00012 | $0.00207 |
Grade A, and why
concise-docs 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 3d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concise Docs
Readers skim: headings first to get the structure, then visuals to get the gist, and prose last to fill in details. These rules turn every section into a unit that can be read at a glance — a format already proven to make documents both quick to read and clear.
Section Rules
A section is any heading (including H1) plus the content directly under it, up to the next heading.
| Rule | Limit | Why |
|---|---|---|
| Visual | At least one ASCII diagram, table, code block, or numbered list of 3+ steps | Structure reads faster as a visual; the visual anchors the section |
| Length | At most 100 Chinese characters; 150 English words | A section that swells breaks the reading rhythm |
| Sentence | At most 50 Chinese characters; 25 English words (soft) | Each extra clause is one more thing to hold in mind |
| Diagram labels | English only inside ASCII diagrams | CJK characters are double-width and break alignment |
| Table | At most 4 columns; at most 15 units per cell | Wide or wordy tables squeeze columns until they stop scanning |
| Emphasis | Bold near 5% of prose (soft); table bold exempt | Emphasis works only when rare; everywhere means nowhere |
| Heading | 2-3 word definite noun phrase (soft); section numbers like 1.1. not counted |
Headings are the table of contents; each should say what is there |
- Only prose counts. Code, diagrams, tables, headings, and URLs are excluded; list items always count, even when a numbered list is the section's visual. Units are CJK characters plus Latin words, inline code counts as one word, and the dominant language picks the limit.
- A pointer section needs no visual: when its content lives elsewhere, one sentence with the link is the whole section — a License section linking to
LICENSE, for example. The script accepts prose within the sentence limit that contains a link. - The introduction under H1 is limited too — a bloated opening is just as uneven.
- A sentence ends at 。！？ or .!?, and every paragraph or list item ends one too. Split a long sentence where a new point starts: a reason, a condition, or an exception usually reads better on its own.
- A heading with only sub-headings and no direct content is a grouping heading and is not checked.
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.
- 3d ago Changed 9391cfa40b17
- 24d ago Changed · +1 lines 8f6589bb1cdb
- 27d ago Changed · +23 lines 54c72102e584
- 1mo ago First seen · 107 lines · 120 tokens per session scan A b607f76932c9
concise-docs is a skill published in the GitHub repository elct9620/claudekit (9 stars, last pushed 3d ago), licensed MIT. It adds 120 tokens to every session and 2,073 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…