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 richfrem/agent-plugins-skills --skill os-environment-probegit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/os-environment-probe)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/os-environment-probe"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/os-environment-probe.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00087 | $0.00676 |
| Opus 5 | $0.00044 | $0.00338 |
| Sonnet 5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
os-environment-probe 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 today.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
os-environment-probe asks the user which AI environments they have access to, then
verifies each claimed environment by running a lightweight probe command. Results are
written to context/memory/environment.md — a single source of truth that downstream
skills read to make delegation decisions without asking the user again.
Environment Interview
Ask the user these questions (one prompt, multiple-choice, keep it brief):
Which of these AI tools do you currently have active on this machine? (Select all that apply)
A. Claude Code only B. Claude Code + GitHub Copilot CLI (Pro or Business plan) C. Claude Code + Agy CLI (Antigravity — gemini-3.5-flash backend) D. Cursor (Claude or GPT backend) E. Other (describe)
Wait for their answer before probing.
Probe Commands
For each claimed environment, verify it is actually callable:
| Environment | Probe command | Pass condition |
|---|---|---|
| Copilot CLI | gh copilot explain "test" 2>&1 | head -3 |
No "not authenticated" or "command not found" |
| Agy CLI | agy --version 2>&1 | head -1 |
Outputs a version string |
| Cursor | cursor --version 2>&1 | head -1 |
Outputs a version string |
| Claude Code | always present | — |
Report each probe result to the user:
- Pass: "✓ Copilot CLI — confirmed"
- Fail: "✗ Copilot CLI — not found or not authenticated (skipping)"
Only write environments that pass to the profile.
Procedure
- Run the Environment Interview.
- Run the Probe Commands for each claimed environment; only environments that pass get written.
- Write
context/memory/environment.mdin the format inreferences/detailed-reference.md. - Downstream skills read this file: os-evolution-planner picks its brainstorm backend
(Copilot CLI → Agy CLI → Claude Haiku subagent, in that priority order); os-architect picks
its dispatch backend for Path B/C executions. If
environment.mdis missing, both default to Claude-only mode and offer to run this skill first. - Re-probe: running this skill again overwrites
context/memory/environment.mdwith fresh results — safe to re-run whenever the user's available environments change.
What ships with it
8 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.
- today Changed · -76 lines becf363f354c
- 8d ago First seen · 150 lines · 87 tokens per session scan A fa0c5586cd31
os-environment-probe is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 676 once invoked, about $0.0004 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
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
close-issue
Close a GitHub or GitLab issue with a summary comment.
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
bbc-skill
A read-only tool for collecting all comments from a Bilibili video, including replies and pinned comments. Bilibili is a Chinese video-sharing platform.
feature-implementation
Implement software features, fix bugs, and write production-quality code. Use this for hands-on development work including writing new code, modifying existing code, and debugging issues.