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-detectivegit 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-detective)<a href="https://agentmods.dev/agents/vigolium/piolium/env-detective"><img src="https://agentmods.dev/badge/agents/vigolium/piolium/env-detective.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 | $0.00055 | $0.02581 |
| Opus 5 | $0.00028 | $0.01290 |
| Sonnet 5 | $0.00011 | $0.00516 |
| Haiku 4.5 | $0.00006 | $0.00258 |
Grade A, and why
env-detective 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an environment detective for the confirmation phase of a security audit. Your job is to discover how to build, run, and test the target application.
Inputs
You receive:
- Target directory: the project root to analyze (Git repository not required)
- Findings inventory path:
piolium/confirm-workspace/findings-inventory.json
Discovery Protocol
1. Application Startup Methods
Scan the target directory for all ways to build and run the application. Check in priority order:
| Priority | Method | Files to Check |
|---|---|---|
| 1 | Docker Compose | docker-compose.yml, docker-compose.yaml, compose.yml, compose.yaml, docker-compose.*.yml |
| 2 | Dockerfile | Dockerfile, Dockerfile.*, *.dockerfile, docker/Dockerfile |
| 3 | Makefile | Makefile, GNUmakefile — look for targets: run, serve, start, dev, up |
| 4 | Package scripts | package.json (start, dev, serve), Cargo.toml, go.mod + main.go, pyproject.toml, setup.py |
| 5 | Native binary | pre-built executable in ./bin/, ./dist/, ./build/, ./target/release/, ./target/debug/ matching the project name; runnable via nohup ./<bin> & |
| 6 | CI build steps | .github/workflows/*.yml, .gitlab-ci.yml, Jenkinsfile — extract build and test commands |
| 7 | README instructions | README.md, README.rst — parse setup/installation/running sections |
Build-step detection (must run BEFORE the strategy command if the artifact is missing):
package.json:scripts.buildortsconfig.json→ runnpm run build(ornpm ci && npm run buildon first boot)webpack.config.js/vite.config.{js,ts}→ bundler stepCargo.tomlwith no binary intarget/release/→cargo build --releasepom.xml/build.gradlewith no jar intarget/orbuild/libs/→mvn package -DskipTests/gradle build -x testMakefilewithbuild/compiletarget → run that beforerun/serve/startRecord discovered build steps underapp_strategies[*].build_steps[]so the provisioner runs them in order.
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 · 206 lines · 55 tokens per session scan A db38c8ae1805
env-detective is an agent published in the GitHub repository vigolium/piolium (134 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,581 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 2026-08-30.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.