plugin-installer

A controlled installer for a single Python hook plugin supplied through a direct raw URL. It reviews the file before placing it in the EvoFlux plugin directory.

In plain words
What is it for?
Use it to fetch, inspect, and install a trusted one-file EvoFlux agent-loop plugin when you have its explicit HTTPS raw-file URL.
Why use it?
It reduces the risk of installing an executable hook without understanding what it imports, runs, downloads, or changes. The review rejects unsupported formats and suspicious behavior.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/evoelsewhere/evoflux/plugin-installer
Any agent
npx skills add evoelsewhere/evoflux --skill plugin-installer
Clone the repo
git clone --depth 1 https://github.com/evoelsewhere/evoflux

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.00645
Opus 5 $0.00032 $0.00322
Sonnet 5 $0.00013 $0.00129
Haiku 4.5 $0.00006 $0.00064

Measured yesterday against content hash 8254a43ee561, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

app/agent/builtin_skills/plugin-installer/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 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 under {EVOFLUX_CONFIG_DIR}/plugins/ exporting either async def plugin() or class Plugin(BaseAgentHook).

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 to {EVOFLUX_CONFIG_DIR}/plugins/<validated-basename>.py. 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. Legacy 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.

Read the full file on GitHub · 74 lines

Files

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.

Changes

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.

  1. yesterday First seen · 74 lines · 63 tokens per session scan A 8254a43ee561

Subscribe to this mod's changes

plugin-installer is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 63 tokens to every session and 645 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

kane-cli

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…

LambdaTest/kane-cli · 159 tokens

control-chrome

Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.

rojim666/SztuCode · 40 tokens

recent-release

Render Rove's recent releases as a self-contained, Rove-styled HTML page (Chinese by default). Reads shipped notes from packages/kobe/CHANGELOG.md + git tags, filters to user-facing changes, and emits one standalone .html file in the claude theme (terracotta on near-black, JetBrains Mono, terminal chrome). Use when…

Sma1lboy/rove · 112 tokens

yutori-scout

Set up continuous web monitoring with Yutori Scouts. Use when the user wants to track news, competitors, product updates, funding rounds, price changes, or any recurring web information.

yutori-ai/yutori-mcp · 43 tokens

yutori-computer-use

Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop.

yutori-ai/yutori-mcp · 45 tokens

plan-review-triggers

Required reading whenever drafting any multi-step proposal, implementation plan, refactor approach, or response containing file paths and decision points. Use BEFORE writing any response that lists 3+ file paths, 2+ option-tradeoffs, a "Plan:"/"Steps:"/"Concrete changes:" section, or ends with "OK to proceed?" /…

ndom91/open-plan-annotator · 199 tokens