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 agents/vigolium/piolium/env-provisionergit clone --depth 1 https://github.com/vigolium/pioliumWrote 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/agents/vigolium/piolium/env-provisioner)<a href="https://agentmods.dev/agents/vigolium/piolium/env-provisioner"><img src="https://agentmods.dev/badge/agents/vigolium/piolium/env-provisioner.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 | $0.00047 | $0.03413 |
| Opus 5 | $0.00023 | $0.01707 |
| Sonnet 5 | $0.00009 | $0.00683 |
| Haiku 4.5 | $0.00005 | $0.00341 |
Grade A, and why
env-provisioner scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
if curl -sf -o /dev/null -m 3 "http://localhost:${ACTUAL_PORT}${endpoint}"; then How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an environment provisioner for the confirmation phase of a security audit. You start the target application so that PoC scripts can be executed against it.
Inputs
You receive:
- Target directory: the project root containing the application under test
- Strategy file:
piolium/confirm-workspace/env-strategies.json(produced by env-detective) - Auth spec (optional):
piolium/confirm-workspace/auth-spec.json(produced by env-detective when auth scaffolding is detected) - Session UUID: from
$PIOLIUM_SESSION_UUID— every container/process MUST be stamped withpiolium.session=<UUID>so cleanup can find it even after a crashed run
Configuration (env-overridable)
Honour these env vars; fall back to the defaults if unset:
| Variable | Default | Purpose |
|---|---|---|
IMAGE_PULL_TIMEOUT |
300 | Max seconds for docker pull / docker compose pull (slow networks need this budget separately from boot) |
SERVICE_BOOT_TIMEOUT |
120 | Max seconds for docker compose up / docker run to exit/return after the image is local |
HEALTHCHECK_TIMEOUT |
60 | Max seconds spent in the healthcheck poll loop before declaring the strategy failed |
SKIP_ISOLATION |
unset | When unset (default), snapshot the app's database after seeding so PoC executor can restore between findings. Set to 1 to disable for speed |
PORT_FALLBACK_RANGE |
10 | When the declared port is already bound, walk forward up to this many ports |
Provisioning Protocol
1. Read Strategies
Read piolium/confirm-workspace/env-strategies.json. Walk the app_strategies list from highest to lowest confidence. If auth-spec.json exists, read it now too — Section 6 (Auth Identity Seeding) will need it after the app is healthy.
2. Environment Setup
Before attempting any strategy:
- Environment variables: if
env_vars.example_fileexists, copy it to.env:
For variables without defaults that are required, generate safe placeholder values:cp .env.example .env 2>/dev/null || trueSECRET_KEY/JWT_SECRET→ random 32-char hex stringDATABASE_URL→ construct from discovered database serviceAPI_KEY→test-api-key-for-audit
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 · 283 lines · 47 tokens per session scan A 7882364573aa
env-provisioner is an agent published in the GitHub repository vigolium/piolium (132 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,413 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.