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/mendix/web-widgets/claude-mdgit clone --depth 1 https://github.com/mendix/web-widgetsWhat 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 | $0.00173 | $0.00173 |
| Opus 5 | $0.00086 | $0.00086 |
| Sonnet 5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
web-widgets 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.
What it actually says
@AGENTS.md
Claude Code
Hooks (auto-applied)
- Auto-format: Every file edit is auto-formatted by prettier via PostToolUse hook.
Do NOT manually run
prettier --write— it wastes tokens, the hook handles it. - Auto-lint: After each edit, eslint runs via
pnpm run lintin the file's package. Lint errors are fed back automatically — fix them in the next edit, do NOT run lint commands manually.
Auto-loaded Documentation
@docs/repo-layout.md @docs/widget-scripts.md @docs/requirements/tech-stack.md @docs/requirements/frontend-guidelines.md @docs/requirements/app-flow.md @docs/requirements/backend-structure.md @docs/requirements/project-requirements-document.md
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 First seen · 21 lines · 173 tokens per session scan A 8f31464e5432
web-widgets CLAUDE.md is an instructions file published in the GitHub repository mendix/web-widgets (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 173 tokens to every session, about $0.0009 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 2026-09-01.
Other instructions, from other repositories
prest copilot-instructions.md
Instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
astron-agent AGENTS.md
Instructions for iflytek/astron-agent, covering agents.md, project overview, repository structure, console and core microservices.
erupt CLAUDE.md
Instructions for erupts/erupt, covering claude.md, build & test commands, build entire project, build a single module (and its dependencies) and skip tests for faster builds.
magic AGENTS.md
Instructions for polterguy/magic, covering agents.md, commands, backend — builds and starts api on http://localhost:5000, frontend — dev server on http://localhost:4201 and one plugin's tests.
nocobase AGENTS.md
AGENTS.md instructions for nocobase/nocobase, covering agents, personal local rules, project structure, code style rules and database & migrations.
easy-vibe CLAUDE.md
Claude Code instructions for datawhalechina/easy-vibe, covering claude.md, project overview, development commands, start local documentation server and build/run commands.