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 mahimailabs/envoic --skill envoicgit clone --depth 1 https://github.com/mahimailabs/envoicWrote 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/mahimailabs/envoic/envoic)<a href="https://agentmods.dev/skills/mahimailabs/envoic/envoic"><img src="https://agentmods.dev/badge/skills/mahimailabs/envoic/envoic/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/mahimailabs/envoic/envoic"><img src="https://agentmods.dev/badge/skills/mahimailabs/envoic/envoic.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 | $0.00101 | $0.00748 |
| Opus 5 | $0.00051 | $0.00374 |
| Sonnet 5 | $0.00020 | $0.00150 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
envoic 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
envoic - Environment Scanner and Cleanup Skill
Use envoic to discover and safely clean Python virtual environments, node_modules, and development artifacts.
Quick Start
uvx envoic scan .
uvx envoic manage . --dry-run
npx envoic scan . --deep
If uvx is unavailable, install Python package with pip install envoic.
If npx is unavailable, install JS package with npm install -g envoic.
Primary Workflows
1) Onboarding Health Check
- Run
uvx envoic info .venv(ornpx envoic info node_modules). - If environment is broken or stale, propose delete-and-recreate steps.
2) Disk Space Recovery
- Run
uvx envoic scan <root> --deepand/ornpx envoic scan <root> --deep. - Identify largest stale candidates.
- Run
manage --dry-run, then actual cleanup only after confirmation.
3) Build/Test Artifact Cleanup
- Scan project root.
- Prefer deleting SAFE artifacts first.
- Warn for CAREFUL artifacts.
Safety Contract
- Always scan before delete.
- Prefer
--dry-runbefore destructive operations. - Never delete lock files or project manifest files.
- Require explicit user confirmation for non-dry-run cleanup.
See full policy in references/safety.md.
Verified Trigger Phrases
- "Find and remove stale virtualenvs"
- "Clean old node_modules and caches"
- "I hit ENOSPC, free up disk from dev artifacts"
- "Audit environment sprawl in this workspace"
- "Check if this .venv is broken"
- "List largest build artifacts"
- "Dry-run cleanup plan for Python and JS"
- "Find dangling venv symlinks"
- "Clean test/build caches safely"
- "Generate JSON report for stale environments"
References
- Full command catalog:
references/commands.md - Safety and risk tiers:
references/safety.md - Troubleshooting and fallbacks:
references/troubleshooting.md
Tool-Specific Surface Files
- Codex:
.agents/skills/envoic/SKILL.md(symlink/copy of this skill) - Cursor:
.cursorrules(generated adapter) - Copilot:
.github/copilot-instructions.md(generated adapter) - Claude:
.claude-plugin/plugins.yaml(generated adapter)
What ships with it
11 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.
- agents/openai.yaml 278 B
- references/commands.md 710 B
- references/safety.md 703 B
- references/troubleshooting.md 679 B
- templates/claude-marketplace.json 184 B
- templates/claude-plugin.json 243 B
- templates/claude-plugins.yaml 253 B
- templates/copilot-instructions.md 1.2 KB
- templates/copilot-repo.instructions.md 500 B
- templates/cursor-rule-envoic.mdc 767 B
- templates/cursor.cursorrules 1.2 KB
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.
- 12d ago First seen · 90 lines · 101 tokens per session scan A 618ea3da223d
envoic is a skill published in the GitHub repository mahimailabs/envoic (6 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 748 once invoked, about $0.0005 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 skills, from other repositories
notion-to-blog
Transfer a blog post from Notion to the Wasp blog. Fetches content, downloads and optimizes images, and creates a properly formatted MDX file.
output-dev-folder-structure
Workflow folder structure conventions for Output SDK. Use when creating new workflows, organizing workflow files, or understanding the standard project layout.
output-dev-code-style
Code style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code. Discovers the project's own linting rules first; falls back to Output SDK conventions when no linter is configured.
output-credentials-init
Initialize encrypted credentials for an Output.ai project. Use when setting up credentials for the first time, adding environment-specific credentials, or adding per-workflow credentials.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
idea-team
A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.