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 instructions/xcirno1/applyer/claude-mdgit clone --depth 1 https://github.com/xCirno1/applyerWrote 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/instructions/xcirno1/applyer/claude-md)<a href="https://agentmods.dev/instructions/xcirno1/applyer/claude-md"><img src="https://agentmods.dev/badge/instructions/xcirno1/applyer/claude-md.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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
applyer CLAUDE.md 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 today.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Guidelines
- Always use production style and compatible code.
- When developing frontend applications, always prioritize user experience (e.g. Use Skeletons when loading data/page, Spinner + disable when performing actions through a button, etc). And, always consider the layout of the page for mobile.
- Always implement full features, do not use "TODO" or "Pending Implementation".
- Never assume that any received data is valid, always verify. This means that if some data is malfunctioned, the app doesn't break and we receive proper logs.
- Always create reusable UI components in a dedicated directory.
- Use proper error handling for ALL code paths with possible errors.
- Always write tests for core logic, capturing all path and edge-cases.
Design Guidelines
- For buttons and other clickable elements, use cursor-pointer on hover.
- Use toast notification for success, errors, or any other events.
- Never use the browser's native
confirm()/alert()/prompt()dialogs. Use a custom modal for yes/no confirmations (e.g. destructive actions) and a toast for one-way notifications. - Use tooltips for idiomatic, technical, and potentially unfamiliar words.
- Instead of expanding down for more sections, try expanding to the right and left.
- For collapsible components that require many actions/informations/fields, consider using modal/dedicated page instead.
Style Guidelines
- Never use icons with background colors and rounded corners.
- Never use blocky UI, i.e. Plain box with rounded corners with some data inside.
- Never use chips with dot on the left side.
- Prioritize rectangle buttons rather than pills.
- Don't hand-tune radii, type sizes, or spacing to taste.
- Don't use em-dashes.
- Density is a feature. Controls are fixed-height (
h-6/h-7), table rows arepy-1.5, panel padding ispx-3. Whitespace between sections should be smaller than you'd use on a content page. - Depth comes from 1px seams and the surface ramp
(
bg-inset<bg<bg-soft<bg-raised), not from shadows, glows, translucency, orbackdrop-blur. Panel fills are opaque and panel edges use full-strengthborder-border;border-border-softis for dividers inside a panel. The only two shadows areshadow-pop(popovers) andshadow-overlay(modals) — both for things that genuinely float. - Chrome should sit still. The top bar and the workspace rail are
opaque bands with hard seams, and everything positioned against the top
bar reads its height from the
navspacing token (--nav-h) rather than restating it.
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.
- today Changed · +1 lines · -2 tokens per session 1a1ef2ed2481
- 5d ago First seen · 47 lines · 746 tokens per session scan A 496a407109cc
applyer CLAUDE.md is an instructions file published in the GitHub repository xCirno1/applyer (7 stars, last pushed yesterday), licensed MIT. It adds 744 tokens to every session, about $0.0037 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 instructions, from other repositories
jobscout-mcp AGENTS.md
AGENTS.md instructions for SarutobiSasuke8/jobscout-mcp: This is the public, vendor-neutral JobScout MCP source and normalization engine.
skillmatch-mcp CLAUDE.md
Claude Code instructions for jarmstrong158/skillmatch-mcp, covering skillmatch mcp server, onboarding flow, tools, setup and getprofile.
host-console AGENTS.md
AGENTS.md instructions for tuweihuasheng/host-console: Run the local server yourself and open the preview in the browser available to this environment. Do not give the user server-start instructions when you can run it.
palmier-pro-windows AGENTS.md
AGENTS.md instructions for MadeNavaneeth/palmier-pro-windows, covering palmier pro windows agent guide, mandatory upstream check, upstream dispositions, translation rules and required finish checks.
ai-plc-integration-public AGENTS.md
AGENTS.md instructions for yihefeikong-rgb/ai-plc-integration-public, covering agents.md — ai 接入 plc, 语言与优先级, 当前工作基线, 变更原则 and plc、tia 与安全边界.
ui-chan-mcp CLAUDE.md
Claude Code instructions for Uncle-Peke/ui-chan-mcp, covering claude.md, what this is, commands, architecture and psd layer convention (psdtool format).