Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add martineserios/thebrana --skill grad-mechanism-designgit clone --depth 1 https://github.com/martineserios/thebranaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/martineserios/thebrana/grad-mechanism-design)<a href="https://agentmods.dev/skills/martineserios/thebrana/grad-mechanism-design"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/grad-mechanism-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/martineserios/thebrana/grad-mechanism-design"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/grad-mechanism-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01129 |
| Opus 5.5 | $0.00016 | $0.00452 |
| Sonnet 5.5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
grad-mechanism-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to grad-mechanism-design — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanism Design: Reverse Game Theory and Incentive Compatibility
Overview
Mechanism design is the engineering side of game theory: instead of analyzing given games, you design the rules so that self-interested agents produce a desired outcome. The central tool is the revelation principle, which shows that any implementable outcome can be achieved by a direct mechanism where truth-telling is optimal. The field underpins auction design, voting systems, matching markets, and regulatory frameworks.
When to Use
- Designing allocation rules (auctions, matching, resource sharing) where participants have private information
- Evaluating whether a proposed institution or platform incentivizes truthful behavior
- Assessing trade-offs between efficiency, budget balance, and participation constraints
When NOT to Use
- Agents are fully cooperative with no private information (no incentive problem exists)
- The environment is too complex to model agent types (use behavioral experiments instead)
- You need a quick heuristic rather than a formal guarantee
Assumptions
IRON LAW: A mechanism is incentive-compatible ONLY if truth-telling is a
dominant strategy — no mechanism can simultaneously maximize efficiency,
budget balance, and individual rationality (Myerson-Satterthwaite theorem).
- Agents are rational and maximize expected utility
- Each agent has private information (type) drawn from a known prior distribution
- The designer commits to the mechanism rules before agents act
- Transfers (payments) are feasible and quasi-linear utility applies
Methodology
Step 1 — Define the Design Problem Specify the set of agents, their type spaces, the outcome space, and the social choice function you want to implement. Identify the objective: efficiency, revenue, fairness, or a weighted combination.
Step 2 — Apply the Revelation Principle Restrict attention to direct revelation mechanisms. For each agent, the mechanism asks for a reported type and maps the profile of reports to an outcome and transfers. Check whether truthful reporting constitutes a Bayesian Nash equilibrium (BNE-IC) or dominant strategy equilibrium (DSIC).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 103 lines · 40 tokens per session scan A 1f4fe95fca5f
grad-mechanism-design is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,129 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to grad-mechanism-design, differing in 15 lines, and is treated as a copy.
Other skills, from other repositories
re-report
A workflow for turning reverse-engineering results into a standard Korean report for beginners. Reverse engineering means examining software to understand how it works.
re-analyze-mycode
A read-only skill for explaining how source code you own or are allowed to inspect works, in beginner-friendly Korean.
help
Show available BMAD commands, agents, and workflows.
bmad-teach-me-testing
Teach testing progressively through structured sessions. Use when user says "lets learn testing" or "I want to study test practices".
onboard
Quick protocol recommendation from recent sessions, or quest-based learning through scenario, trial, and quiz.
async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…