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 tmusser/ai-engineering-skills --skill operator-profilegit clone --depth 1 https://github.com/tmusser/ai-engineering-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/tmusser/ai-engineering-skills/operator-profile)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/operator-profile"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/operator-profile/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/tmusser/ai-engineering-skills/operator-profile"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/operator-profile.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 | $0.00029 | $0.01086 |
| Opus 5.5 | $0.00012 | $0.00434 |
| Sonnet 5.5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
operator-profile 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 10d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator Profile
Purpose
Configure how AI Engineering Skills should behave for a particular operator without turning personal preferences into a second task contract.
Setup skill, not a workflow stage. Run it when preferences are first established or materially change, then let other skills consume the profile as a default.
The profile may narrow authority; it may not grant new authority.
When to use
Use when the operator wants recurring defaults for ceremony, autonomy, verification depth, communication density, or ambiguity handling.
Do not run it for every task. Skip it when the current request already gives the needed preferences or when no persistent personalization is useful.
Inputs
- Explicit operator preferences
- Optional existing native user/project instructions
- Optional project-specific preferences
- Intended profile scope: session, project, or user
Do not infer durable preferences from one-off behavior, a single terse request, or temporary task pressure.
Authority boundary
An operator profile is a preference layer, not an authorization layer.
A current explicit instruction, repository-native instruction, task contract, safety boundary, tool permission, scope freeze, verification requirement, or human gate outranks a profile default when they conflict.
The profile may make behavior stricter. It must not:
- expand write scope, tool access, permissions, or side effects
- weaken required verification, compatibility probes, or review gates
- convert a human approval boundary into autonomous permission
- override a named acceptance criterion, non-goal, or repository rule
- hide material ambiguity merely because the operator prefers fewer questions
Workflow
- Establish the intended profile scope:
session,project, oruser. - Capture only these recurring defaults:
- Ceremony preference:
lean | balanced | guarded - Autonomy boundary:
propose-only | bounded-execution | human-gate-side-effects - Verification depth:
targeted | standard | expanded - Communication density:
lean | normal | explanatory - Ambiguity handling:
ask-material | safe-reversible-assumptions
- Ceremony preference:
- Ask at most five compact questions, and only for fields that are genuinely unknown or materially affect the profile.
- If a project needs a local exception, record it as a project-specific note rather than silently changing the broader operator default.
- Emit one compact profile block.
- If persistence is wanted, place the block in an existing agent-native user or project instruction surface, or another explicitly chosen configuration surface. Do not invent a second instruction hierarchy.
- Re-run setup only when preferences materially change.
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.
- 10d ago First seen · 131 lines · 29 tokens per session scan A b91591cc2c41
operator-profile is a skill published in the GitHub repository tmusser/ai-engineering-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,086 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
dwi-budget
Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.
concise-mode
Use this skill to enforce high-density, zero-filler, token-efficient communication. Strips conversational fluff, polite preamble, redundant summaries, and repetitive apologies to maximize reasoning density, reduce latency, and conserve context window budget.
orbit-general
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
discovery-question-form
Structured clarification form for unresolved material requirements.
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.