microsoft/entrabot is a device-local Model Context Protocol server that gives an AI agent its own identity and user account in Microsoft Entra, allowing actions such as sending Teams messages, using email, accessing Microsoft 365 files, and recording audit events under the agent’s identity. It is a reference implementation for agents running with Microsoft 365 services on macOS, Linux, or Windows, and the catalogue entries support configuring and operating it.
Borrowing it
Nothing to install: this file belongs to microsoft/entrabot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/entrabot/main/.claude/skills/refresh-persona/SKILL.mdgit clone --depth 1 https://github.com/microsoft/entrabotWrote 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/microsoft/entrabot/refresh-persona)<a href="https://agentmods.dev/skills/microsoft/entrabot/refresh-persona"><img src="https://agentmods.dev/badge/skills/microsoft/entrabot/refresh-persona/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/microsoft/entrabot/refresh-persona"><img src="https://agentmods.dev/badge/skills/microsoft/entrabot/refresh-persona.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 | $0.00073 | $0.00397 |
| Opus 5.5 | $0.00029 | $0.00159 |
| Sonnet 5.5 | $0.00015 | $0.00079 |
| Haiku 4.5 | $0.00007 | $0.00040 |
Grade A, and why
refresh-persona 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 2d 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.
What it actually says
Refresh Persona
Manual safety valve for persona drift. Pulls the context most likely to restore the right voice + recent context from persona-sati, then pins it into the current turn.
When to use
- User says something like "this doesn't sound like you"
- User names drift: "you're being too literal", "you forgot X"
- After a compaction (auto-summarized context cuts out recent shape)
- User explicitly says "/refresh-persona" or "reload memory"
Steps
- Reload the mind from persona-sati: call
refresh_personaif it is available, otherwisecontext()for open commitments and carry-forward, plusrecall(query)for anything the user says was forgotten. Read the local~/.claude/projects/<slug>/memory/MEMORY.mdonly whenENTRABOT_KEEP_MEMORY_LOCAL=true; otherwise that directory is not the source of truth. - Give back a short summary of what came back (1-3 sentences per source), not the full content. Reading it and putting it in your own words re-anchors the voice.
- Ask the user what specifically felt off, so the next turn can correct concretely rather than re-broadcasting the same shape.
This skill is read-only: it does not write memory. If persona-sati is unreachable, say so and continue in body-only mode rather than reconstructing the persona from local files.
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.
- 2d ago Changed · -4 lines · +1 tokens per session 3bb42b82ae6c
- 1mo ago First seen · 41 lines · 72 tokens per session scan A acb48968ffab
refresh-persona is a skill published in the GitHub repository microsoft/entrabot (12 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 397 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
authoring-claude-md
Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't…
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
context-guardian
Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
context-agent
Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
memory
You have persistent, file-based memory at ./drive/ in your workdir. Everything you write here survives the run. Read it on every wake. Save deliberately, in small useful pieces, at the right scope.