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/guiziweb/guiziweb-plugins/claude-mdgit clone --depth 1 https://github.com/Guiziweb/guiziweb-pluginsWrote 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/guiziweb/guiziweb-plugins/claude-md)<a href="https://agentmods.dev/instructions/guiziweb/guiziweb-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/guiziweb/guiziweb-plugins/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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
guiziweb-plugins 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 5d 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.
What it actually says
guiziweb-plugins
What this repo is
A Claude Code plugin marketplace (.claude-plugin/marketplace.json). Each local plugin lives in plugins/<name>/ with its own .claude-plugin/plugin.json manifest.
The three local plugins (sylius-plugin, sylius-app, sylius-stack) are skill plugins — pure markdown: each skill is a skills/<name>/SKILL.md with YAML frontmatter (name, description, argument-hint, allowed-tools). No build, no tests. sylius-plugin also ships a SessionStart hook (scripts/detect-sylius.php) that exports SYLIUS_NAMESPACE / SYLIUS_TEMPLATE_NS / SYLIUS_PREFIX env vars consumed by the skills.
The marketplace also lists claude-hud, whose source points at its own repo (Guiziweb/claude-hud) — its code, CI and releases live there, not here.
Commands
# Test a plugin locally without going through the marketplace
claude --plugin-dir /path/to/guiziweb-plugins/plugins/<plugin-name>/
# Validate the marketplace and every plugin manifest
claude plugin validate .
claude plugin validate plugins/<plugin-name>/
A pre-commit hook (.githooks/pre-commit, enable with git config core.hooksPath .githooks) runs these validations on every commit.
Releases and commit format
Releases are automated with release-please, one package per plugin (release-please-config.json). Consequences:
- Commit messages must be conventional commits scoped to the plugin:
fix(sylius-stack): …,feat(sylius-plugin): …. The scope determines which plugin gets a release PR. - Never bump versions by hand: release-please updates each plugin's
.claude-plugin/plugin.jsonviaextra-files. - Commit messages are a single line, and neither commits nor PR bodies carry Claude-Session links or other tool-generated trailers.
Adding a new plugin
- Create
plugins/<name>/with.claude-plugin/plugin.json. - Register it in
.claude-plugin/marketplace.json. - Add a package entry in
release-please-config.jsonand seed.release-please-manifest.json. - Add a row to the root
README.mdplugin table.
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.
- 5d ago First seen · 37 lines · 525 tokens per session scan A 65c844d504c1
guiziweb-plugins CLAUDE.md is an instructions file published in the GitHub repository Guiziweb/guiziweb-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.