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 evoelsewhere/evoflux --skill plugin-installergit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/plugin-installer)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/plugin-installer"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/plugin-installer/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/evoelsewhere/evoflux/plugin-installer"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/plugin-installer.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 | $0.00092 | $0.00704 |
| Opus 5.5 | $0.00037 | $0.00282 |
| Sonnet 5.5 | $0.00018 | $0.00141 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
plugin-installer 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 22d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install a single-file EvoFlux plugin
Plugins run in-process with agent permissions. Treat installation as executable
code review, not ordinary file download. The supported runtime contract is one
.py file in the plugins/ subdirectory of the EvoFlux configuration
directory (its absolute path is stated in the Skills section of the system
prompt), exporting either async def plugin() or
class Plugin(BaseAgentHook). Below, "the plugin directory" means that
plugins/ subdirectory.
State machine
1. FETCH
Require an explicit https:// raw Python URL. Fetch read-only into a temporary
location. Reject redirects or responses that produce HTML, an archive,
multiple files, a dependency manifest, an absolute/traversal filename, a
leading-underscore filename, or a non-.py basename.
2. INSPECT
Read the complete file. Require one supported entry point and inspect imports, top-level execution, subprocess/network/file access, secret handling, dynamic evaluation, persistence, and hook mutations. Show the user the source URL, target filename, entry point, material capabilities, and suspicious behavior; do not reduce review to checking one string.
Do not install code that downloads additional executable content, embeds credentials, disables permission boundaries, or cannot be understood as a single-file hook. Do not author or repair untrusted plugin code inside this workflow.
3. RESOLVE COLLISION
If the target exists, read it and show the material diff. An explicit request to "update" authorizes replacement only after the fetched code and diff have been shown; an ambiguous install collision requires confirmation. Preserve the existing file when validation or approval fails.
4. INSTALL
Write exactly one file, <validated-basename>.py, into the plugin directory.
Do not create package directories, install dependencies, or touch unrelated
plugins.
5. VERIFY
Read the installed file back, confirm its hash/content matches the reviewed payload, and validate that the entry point remains present. Hook plugins are cached per agent/role, so report that a runtime restart is required before the new or replaced hook is reliably active. Never claim activation merely from a successful write.
What ships with it
2 files 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.
- 22d ago Changed · +4 lines · +29 tokens per session 65047dafbf7c
- 1mo ago First seen · 74 lines · 63 tokens per session scan A 8254a43ee561
plugin-installer is a skill published in the GitHub repository evoelsewhere/evoflux (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 704 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
review-diff
Review the working-tree diff for bugs and over-engineering.
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
3D模型与视频特效
A tool for generating 3D models from text or images and applying preset animated effects to pictures. It does not generate ordinary images or full videos.
tencent-docs-sheet-generation
A tool for creating a new Excel workbook (.xlsx) from written requirements or reference PDF, Word, or presentation files. It is for starting without an existing spreadsheet file.
html-to-docx
A converter that turns HTML into an editable Microsoft Word document (.docx). It maps common HTML structure and styles, and can include images, tables, a table of contents, headers, and footers.
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.