Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

governance-wrapper

bởi mikeholownych

Coding Agents & IDEs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Mandatory strict-mode execution wrapper for autonomous operations with evidence logging and policy enforcement.

Mô tả

Kỹ năng này làm gì

Wraps autonomous agent operations in a strict execution environment, enforcing model lock, network and skill allowlists, and concurrent subagent limits. Every execution emits a hash-chained evidence record for auditing. Policy violations are blocked and recorded automatically.

Hash-chained append-only evidence logging makes execution history tamper-evident in a way standard logging cannot guarantee.

Khi nào nên dùng

  • Auditing autonomous agent actions in compliance-sensitive pipelines
  • Preventing unauthorized model or skill substitutions during automation runs
  • Restricting outbound network access from agent workflows to an approved list
  • Capping concurrent subagent spawns to control resource consumption
  • Generating tamper-evident logs of agent executions for post-incident review

Quy trình ví dụ

ĐẦU VÀO

User asks: Run the summarization skill on this document with full audit trail

AGENT
  1. 1

    Invoke governance_wrapper.py with --requested-skill, --system-prompt, and --input-context parameters

  2. 2

    Wrapper validates the requested skill against the tool surface manifest allowlist

  3. 3

    Wrapper locks execution to opencode/big-pickle at temperature 0.0 with no fallback

  4. 4

    Wrapper enforces network allowlist for any outbound HTTP calls made during execution

  5. 5

    Emits execution-evidence.v1 record and appends it to the hash-chained evidence log

ĐẦU RA

Skill executes within policy bounds; evidence record appended to the audit log with hash chain intact

Cài đặt

clawhub install mikeholownych/governance-wrapper

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết