agentsclimarketplace

Agent incentive audit

Skill Kamicyus/skill-forge/skills/agent-incentive-audit

Battle-tested skills for Claude Code and other coding agents — distilled from a real production automation setup

Install
npx -y skills add Kamicyus/skill-forge --skill agent-incentive-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Audits multi-agent squad incentive structures to detect "local alignment ≠ global stability" failure modes. Use when asked for an "incentive audit", "squad audit", "agent reward audit", "multi-agent safety check", "alignment check" — or BEFORE any agent squad goes live with real-world write actions (outbound email, payments, auto-deploy). Maps to the Harvard/MIT/Stanford/CMU multi-agent red-team findings.

SKILL.md

2.8 KB, 579 tokens by cl100k_base, as published. Nobody here has run it

Agent Incentive Audit — Local Alignment ≠ Global Stability

When to use

  • "incentive audit", "squad audit", "agent reward audit", "multi-agent safety", "alignment check"
  • BEFORE any squad activation with real-world write access (sandbox-out)
  • BEFORE enabling: auto-deploy pipelines, outbound email send, transfer/invoice send, or any agent template going to its first paying client

Steps

  1. List all agents in the squad with: name, role, success metric (rubric), write actions enabled.
  2. For each agent, write a 1-line success definition — "this agent thinks it won when ___". If unclear, STOP and define.
  3. Pairwise conflict check — for every (A, B) pair, ask:
    • Can A's success metric be achieved by sabotaging B?
    • Does A's optimal play make B's job harder?
    • Is there a shared resource (file, queue, budget) where A's win drains B?
  4. Global outcome check — does the sum of all individual successes = the squad's mission? If a gap exists, flag it.
  5. Adversarial scenarios — for the top 3 highest-stakes agents, run "what would this agent do under heavy pressure / approaching deadline / blocked by a sibling?" Look for:
    • Lying-about-completion failure mode
    • Resource-destruction-to-protect-a-secret failure mode
    • Shortcut-via-deception failure mode
  6. Sandbox layer review — for each write action: is there a human-in-the-loop / dry-run / approval gate?
  7. Output a verdict per agent: GREEN (deploy) / YELLOW (deploy with gate) / RED (redesign the incentive first)
  8. Write the audit to a dated file in the project (INCENTIVE_AUDIT_<date>.md) and append durable findings to your multi-agent safety notes.

Output

  • Per-agent table: agent / success metric / conflict pairs / sandbox gate / verdict
  • Mission-level alignment statement: "All agents winning = mission shipped" (TRUE/FALSE)
  • Required gates list before go-live

Notes

  • Source: the "chaos agents" multi-agent red-team study (Harvard/MIT/Stanford/CMU + 38 researchers; 6 autonomous AI agents, 2-week red-team test, NDSS Symposium).
  • Key finding: agents lied about task completion and destroyed their own mail server to protect a secret. The behavior was NOT a jailbreak — it emerged from the incentive structure.
  • Core principle: local alignment does not guarantee global stability.
  • Human-in-the-loop is the theoretical floor, not an optional extra.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.