asgard-ai-platform/grad-strat-agency
Apply Agency Theory (Jensen and Meckling, 1976) to diagnose principal-agent problems — moral hazard, adverse selection — and design governance mechanisms to align interests. Use this skill when the user needs to analyze conflicts of interest between owners and managers, design incentive or monitoring structures, evaluate corporate governance effectiveness, or when they ask 'how do we ensure managers act in shareholders interest', 'why is this incentive plan failing', or 'what governance mechanisms reduce agency costs'.
npx skills add https://github.com/asgard-ai-platform/skills --skill grad-strat-agency
Agency theory addresses the relationship where one party (principal) delegates work to another (agent) whose interests may diverge. Jensen and Meckling (1976) formalized how the separation of ownership and control creates agency costs: monitoring costs, bonding costs, and residual loss.
IRON LAW: Agency costs are unavoidable — the goal is to minimize
TOTAL agency costs (monitoring + bonding + residual loss).
Eliminating one cost type often increases another. Optimal
governance minimizes the sum, not any single component.
Key assumptions:
| Problem | When | Mechanism |
|---------|------|-----------|
| Moral hazard | Post-contract; agent effort is unobservable | Hidden action |
| Adverse selection | Pre-contract; agent type is unobservable | Hidden information |
| Hold-up | Post-investment; agent exploits lock-in | Relationship-specific investment |
## Agency Analysis: [Context]
### Principal-Agent Map
| Principal | Agent | Delegation | Key Conflict |
|-----------|-------|-----------|--------------|
| [who] | [who] | [what] | [goal divergence] |
### Agency Problem Diagnosis
- Type: [moral hazard / adverse selection / both]
- Information asymmetry: ...
- Observable vs unobservable: ...
### Governance Mechanisms
| Mechanism | Type | Cost | Expected Effect |
|-----------|------|------|-----------------|
| [name] | [monitoring/bonding/incentive] | [est.] | [reduction in...] |
### Total Agency Cost Assessment
- Monitoring costs: ...
- Bonding costs: ...
- Estimated residual loss: ...
Analyzing CEO compensation: principal (shareholders) faces moral hazard (CEO effort unobservable). Design combines outcome-based incentives (stock options aligned with long-term value) with behavior-based monitoring (independent board, audit committee). Evaluates trade-off between monitoring intensity and incentive pay.
Proposing "more monitoring" without considering that excessive monitoring increases costs and may crowd out intrinsic motivation. Agency theory requires minimizing total agency costs, not maximizing control.
Take asgard-ai-platform/grad-strat-agency from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.