For PE ops and portfolio CFOs running agents on portco data: 10 Claude prompts plus AGT install path, three policy YAML templates, OWASP verify runbook, and entity scoped read gates. Replaces prompt level be careful with structural deny.
Never used Claude? It is free and takes 30 seconds to open. Copy the instruction below, paste it into Claude, and it reads this page and walks you through everything, one question at a time.
A short instruction plus a link to this page lands on your clipboard. First copy asks for your email once. That unlocks every button across the whole library.
Free account, no card, 30 seconds. This tab stays open so you can come back.
Open claude.ai ↗Claude reads this page, asks which computer you are on, then guides you step by step until it works. If anything errors, tell Claude what you see, and it fixes it with you.
If you can browse the web, open and read this page in full first, it has the complete guide and every prompt you will run (the vault is under the-vault anchor): https://consultance.ai/library/agent-governance-kit#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts. I want to set up agent governance for Claude agents that touch portfolio exports, using Microsoft's Agent Governance Toolkit plus the policy templates on this page. Walk me through it step by step, one question at a time. I may be PE ops, portfolio CFO, or model risk. This is a hybrid install: Python for AGT enforcement, Claude for analysis. Define every term once. ## Honest ceiling, up front AGT is public preview MIT software from Microsoft. It intercepts tool calls in code. It does not replace your SOC 2 program, DPA, or named human sign off. Prompts in the vault are the design layer. Reply "wire it" when you need live export paths and govern() on every tool. ## What this produces Policy YAML for portfolio read only, finance send gates, and multi agent identity. A verified install path (pip install agent-governance-toolkit[full], agt doctor, Claude Code plugin). OWASP verify and red team commands run before go live. Entity scoped reads so two portcos cannot bleed on one screen. ## Step one, ask me this first, nothing else "Which install path fits you today: (A) Python pip on your machine or VPC, (B) Claude Code with the AGT plugin, (C) Claude app only for policy design before any install, or (D) hybrid pip plus Claude app?" Wait for my answer. Then continue, one step per message. ## Hybrid paths **Path A (Python):** One command at a time. pip install agent-governance-toolkit[full]. Then agt doctor. Create policies/ and copy the three YAML files from policy-templates.md on this page. Show me govern() wrapped around one read tool and one write tool. A denied action must raise GovernanceDenied. **Path B (Claude Code):** /plugin marketplace add microsoft/agent-governance-toolkit then /plugin install agt-governance@agent-governance-toolkit. Run agt doctor from the integrated terminal. **Path C (Claude app only):** Upload policy-templates.md and prompt 01 from the vault into a private Project. Design policies before touching live exports. All paths: before go live run agt verify --evidence ./agt-evidence.json --strict and agt red-team scan ./prompts/ --min-grade B. Prompt 07 in the vault is the runbook. ## First session drill I should end with one policy file linted, one tool wrapped with govern(), one intentional deny proven, and prompt 07 marked PASS. No production data until entity scoped read policy is active. Anti-pattern: do NOT tell me "please follow the rules" in the system prompt is enough. OWASP says prompt injection cannot be foolproof. Related: [[enterprise-automation-pack]] · [[enterprise-ai-perimeter]]
Grab the whole pack as one file, or tap any prompt below to copy it on its own. Placeholders that look like {{THIS}} get swapped for your own numbers — and if you ran Step 1, Claude fills them in for you.
For PE ops and portfolio CFOs running agents on portco data: 10 Claude prompts plus AGT install path, three policy YAML templates, OWASP verify runbook, and entity scoped read gates
The setup rail and every prompt above are free and stay free. The cost is your time, and the risk of wiring it wrong on live data.
Back to the prompts ↑This kit is about 70% of the build. We wire the last 30% into production: live export paths with entity folders, govern() on every tool your agent uses, perimeter stack with enterprise-ai-perimeter, LP evidence pack filed in your GOVERN folder, and human approval gates your auditor will accept. Reply wire it for a 30 minute slot.
Book a build call →Prompt set authored by consultance.ai. Agent Governance Toolkit is MIT licensed public preview from Microsoft at https://github.com/microsoft/agent-governance-toolkit. AGT does not replace SOC 2, DPA, or named human sign off. You supply your own Claude tenant and portfolio exports.
Want this wired into your stack instead of running it yourself? That is our AI deal desk and finance automation service.
The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.
More like this
For founders, CFOs, and deal teams: 9 Claude prompts that rebuild the cap table from the signed documents instead of the spreadsheet, run the waterfall clause by clause against the actual LPA or charter, and recompute fee and carry independently, so a stale sheet gets caught before a round closes on it.
For CFOs and finance leaders: the map of seven finance desks, deal, diligence, close, tax, underwriting, family office, and market, each one a free prompt vault that runs inside your own Claude, plus the order to install them in so a team actually adopts them.
For CFOs and controllers: 11 Claude prompts that run the month end close reconciliation itself, match bank and subledgers both directions, catch the account that will not foot, and draft the flux memo, so a 6 day close lands in 2.
The person drowning in this every week is the one who'll actually want it.
Agent Governance Kit is a finance and data build in the consultance.ai AI Build Library. For PE ops and portfolio CFOs running agents on portco data: 10 Claude prompts plus AGT install path, three policy YAML templates, OWASP verify runbook, and entity scoped read gates. Replaces prompt level be careful with structural deny. It fits PE ops leads, portfolio CFOs, finance agent owners, and model risk teams who need deterministic control over what Claude agents can read, write, and send across multiple portfolio companies, and who learned entity bleed is an architecture problem not a prompt problem.. Setup difficulty is Medium, with 5 plain-English steps.
For PE ops and portfolio CFOs running agents on portco data: 10 Claude prompts plus AGT install path, three policy YAML templates, OWASP verify runbook, and entity scoped read gates. Replaces prompt level be careful with structural deny.
It fits PE ops leads, portfolio CFOs, finance agent owners, and model risk teams who need deterministic control over what Claude agents can read, write, and send across multiple portfolio companies, and who learned entity bleed is an architecture problem not a prompt problem..
Medium to set up — one guided setup instruction covering 5 plain-English steps, plus 10 ready-to-run prompts on the resource page.
This kit is about 70% of the build. We wire the last 30% into production: live export paths with entity folders, govern() on every tool your agent uses, perimeter stack with enterprise-ai-perimeter, LP evidence pack filed in your GOVERN folder, and human approval gates your auditor will accept. Reply wire it for a 30 minute slot.
Prompt set authored by consultance.ai. Agent Governance Toolkit is MIT licensed public preview from Microsoft at https://github.com/microsoft/agent-governance-toolkit. AGT does not replace SOC 2, DPA, or named human sign off. You supply your own Claude tenant and portfolio exports.
Agent Governance Kit is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.
This build comes from our AI consulting and AI implementation practice — see the full AI in finance guide and how we work with CFO teams.