ClawMaven

By Master 22 Solutions LLC

Overview

Work with your saved ClawMaven governance profiles before you deploy an AI agent. Get a profile's posture score, grade, and category breakdown; retrieve the effective policy (allowed tools, blocked domains, budget caps, and autonomy level) for an agent you name; check an agent's USD spend against the profile's budget cap; and generate a signed trust manifest for deployment. Recording monthly spend requires your authorization. ClawMaven is pre-deployment governance design: it does not scan code, monitor agents, or enforce policy at runtime.

Tools

check_budget_cap

ChatGPT

Check a run's USD spend against the per-run budget cap in a saved Clawmaven governance profile. Read-only: records nothing and does not block anything; the agent's runtime enforces the cap. Use only when the user asks about a specific saved ClawMaven governance profile or agent; do not use for general questions about AI governance, security or ClawMaven itself.

generate_trust_manifest

ChatGPT

Generate a new signed trust manifest for an agent's saved governance profile, posture grade, allowed tools, and budget cap. Signed with HMAC-SHA256; each call produces a new manifest identity and expiry. Use only when the user asks about a specific saved ClawMaven governance profile or agent; do not use for general questions about AI governance, security or ClawMaven itself.

get_effective_policy

ChatGPT

Read the effective policy a saved Clawmaven governance profile sets for an agent: allowed tools, blocked domains, per-run and monthly budget caps, autonomy level and approval gates. Read-only. ClawMaven does not apply or enforce the policy; the agent's runtime does. Use only when the user asks about a specific saved ClawMaven governance profile or agent; do not use for general questions about AI governance, security or ClawMaven itself.

get_posture_score

ChatGPT

Compute the governance posture score for a saved Clawmaven governance profile. This is a governance posture assessment of the saved configuration, not a security or vulnerability scan. Returns an overall score (0–100), a letter grade (A–F), and per-category breakdowns. Use only when the user asks about a specific saved ClawMaven governance profile or agent; do not use for general questions about AI governance, security or ClawMaven itself.

record_monthly_spend

ChatGPT

Record a USD spend increment for an agent against the monthly budget cap in a saved Clawmaven governance profile, and report the month-to-date total and what remains of the cap. Writes to the server's monthly spend ledger: call it only when the user asks to record spend, with one idempotencyKey per spend event (a retry with the same key is not counted twice). For a read-only per-run check, use check_budget_cap. ClawMaven does not block actions; the agent's runtime enforces the cap. Use only when the user asks about a specific saved ClawMaven governance profile or agent; do not use for general questions about AI governance, security or ClawMaven itself.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Links

Documentation Privacy Policy

Similar Apps