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 JuanMarchetto/agent-skills --skill hackathon-jurygit clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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/juanmarchetto/agent-skills/hackathon-jury)<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/hackathon-jury"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/hackathon-jury/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/juanmarchetto/agent-skills/hackathon-jury"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/hackathon-jury.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 | $0.00084 | $0.01199 |
| Opus 5.5 | $0.00034 | $0.00480 |
| Sonnet 5.5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
hackathon-jury 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hackathon Jury Simulator
Simulate a complete hackathon jury evaluation. Given a project and a hackathon event name, this skill researches the real jury members, builds personalized juror personas, and evaluates the project from each juror's perspective.
How It Works
- Project Discovery — analyze the project's architecture, code quality, README, and git history
- Hackathon Research — use WebSearch to find real jury members, judging criteria, past winners, and sponsor priorities (see
agents/researcher.md) - Jury Construction — build 3-7 juror personas based on real people or representative archetypes
- Parallel Evaluation — dispatch each juror as a parallel agent using
agents/juror.md, each evaluating from their unique perspective - Deliberation Synthesis — simulate jury deliberation using
agents/synthesizer.md, resolving disagreements and estimating placement
Usage
"Evaluate my project for the Colosseum Eternals hackathon"
"How would the ETHGlobal Bangkok judges score this repo?"
"Prep me for the Solana Breakpoint hackathon — judge my submission at ./my-project"
Output
The evaluation produces:
- Verdict Overview — overall score, placement estimate, one-sentence consensus
- Jury Scorecard — per-criterion scores from each juror with weighted averages
- Individual Juror Feedback — what impressed them, what concerned them, questions they'd ask
- Deliberation Simulation — points of agreement, debate, and what would swing the decision
- Competitive Position — strength vs typical submissions, what would beat this project
- Improvement Roadmap — max 7 prioritized actions (quick wins + strategic moves)
- Pitch Coaching — optimal demo flow, buzzwords, what to emphasize vs downplay
Agent Files
| Agent | Purpose |
|---|---|
agents/researcher.md |
Researches hackathon event, jury members, criteria, past winners, sponsors |
agents/juror.md |
Role-plays as a specific juror, evaluates from their perspective |
agents/synthesizer.md |
Simulates deliberation, produces unified verdict and recommendations |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 94 lines · 84 tokens per session scan A 16bf73989afe
hackathon-jury is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 1,199 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
hackathon-jury compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hackathon-juryJuanMarchetto/agent-skills | Skill | 5 | 7mo ago | MIT | A | 84 | Claude Code |
| x402browser-use/browser-use | Skill | 121k | yesterday | MIT | A | 166 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 54 | Claude Code, Codex |
| open-sourcebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 101 | Claude Code |
| remote-browserbrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 22 | Claude Code |
| cloudbrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 177 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | 4d ago | Apache-2.0 | A | 61 | Claude Code |