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 naveedharri/benai-skills --skill os-operatorgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/os-operator)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/os-operator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/os-operator/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/naveedharri/benai-skills/os-operator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/os-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 8 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.
- medium Excessive Agency · line 259 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 | $0.00192 | $0.04403 |
| Opus 5 | $0.00096 | $0.02201 |
| Sonnet 5 | $0.00038 | $0.00881 |
| Haiku 4.5 | $0.00019 | $0.00440 |
Grade A, and why
os-operator 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OS Operator
Build a personalized Operator prompt that runs the user's second brain on a recurring schedule. The Operator is a fully autonomous maintenance agent — one session = one run, no questions, no confirmations, executes and reports.
This skill does four jobs, in order:
- Discover what the vault already knows. Read
Context/andCLAUDE.mdsilently — extract org name, team scope, brand voice, vault folders, runtime conventions. - Ask only the gaps. Cadence, connectors, DM recipient, budgets, signature. Don't re-ask anything Phase 0 already pulled out of the vault.
- Render and save the personalized prompt locally.
- Schedule it. Hand off to the
scheduleskill (via theSkilltool) so the trigger is wired before the run ends — the user does not need to manually run/schedule create.
Reference files
references/operator-prompt-template.md— the parameterized prompt. ~400 lines, preserves every critical rule from the source spec.references/connector-fragments.md— spliceable body blocks per connector (transcripts, chat, community).
Read both before generating output.
Phase 0 — Silent discovery (no questions, no MCP calls)
The user invokes this skill from inside their vault folder locally. Everything here is filesystem-only. Do NOT call any vault_* MCP tools — the Vault MCP only matters at runtime when the rendered Operator agent runs.
-
Verify the cwd is a vault.
claude.mdorCLAUDE.mdmust exist at the cwd root. If neither exists, ask the user tocdinto their vault and re-run. Do not proceed. -
List top-level folders.
Globpattern*/at cwd. Cache the result as{{VAULT_FOLDERS}}(one folder name per line). -
Read
CLAUDE.md. Pull conventions: signature style, em-dash rule, voice rules, folder routing, any explicit operator paths,os-mode(professional vs business). -
Find the curated layer, then read it by subject. Do not assume it is called
Context/.Resolve it: the folder named in
CLAUDE.md's routing table as holding identity, brand or strategy; else a top-level folder from{{VAULT_FOLDERS}}namedContext,About,Me,Identity,Personal,Brandor similar; else the folder whose files actually carry that content. Cache it as{{CONTEXT_ROOT}}.
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.
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 · 265 lines · 192 tokens per session scan A c78e920b6578
os-operator is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 7d ago), licensed MIT. It adds 192 tokens to every session and 4,403 once invoked, about $0.0010 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 2026-09-05.
Other skills, from other repositories
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.
marketing-meta-ads-manager
A skill that manages Facebook and Instagram advertising through Meta’s official connector using natural-language instructions.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
collab-conflict
A guide for handling difficult workplace colleagues and recurring communication conflicts.
collab-feedback-loop
A guide for giving and receiving workplace feedback about specific actions and their effects.
collab-meeting
A meeting facilitation aid that helps define the purpose, plan the agenda, guide discussion, record decisions, and assign follow-up actions.