Borrowing it
Nothing to install: this file belongs to 82deutschmark/arc-explainer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/82deutschmark/arc-explainer/main/.agents/skills/competition-reporter/SKILL.mdgit clone --depth 1 https://github.com/82deutschmark/arc-explainerWrote 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/82deutschmark/arc-explainer/competition-reporter)<a href="https://agentmods.dev/skills/82deutschmark/arc-explainer/competition-reporter"><img src="https://agentmods.dev/badge/skills/82deutschmark/arc-explainer/competition-reporter/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/82deutschmark/arc-explainer/competition-reporter"><img src="https://agentmods.dev/badge/skills/82deutschmark/arc-explainer/competition-reporter.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 | $0.00041 | $0.00867 |
| Opus 5.5 | $0.00016 | $0.00347 |
| Sonnet 5.5 | $0.00008 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
competition-reporter 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 12d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competition reporter
Follow the people and the sporting consequence. Lead with the strongest verified result, move or research announcement; use the standings to explain the stakes. A quiet day can warrant a short report. Biographies belong where they help readers understand a contender.
Evidence and identities
- Use the competition's exact ID, season and team ID as its entry key. A person's stable ID is separate: one person can have different teams in different contests or seasons.
- Connect a handle to a person through direct profile links, credited write-ups or primary professional sources. Similar names and matching avatars do not establish identity. Keep unresolved handles unresolved.
- Save narrow facts with primary source URLs and check dates. Preserve dated team roster observations; they establish presence at that time, not a joining date, departure, leadership or responsibility for a score. Preserve historical memberships when a later board omits them.
- Cross-reference relevant existing achievements and artwork. Identify historical years clearly; a shared team card does not establish a current roster. Reuse an archive's explicit identity mapping.
- Separate team and individual accomplishments. A one-account roster supports “one listed account”; it does not prove nobody helped. Explain verified affiliations without extending them to every team member.
Show the people
Readers follow faces. Give every verified person one portrait from a source tied to that identity: archive art made of them alone, or the profile picture on their own verified account. Never crop a face out of a group image, use a lookalike, or keep a picture its owner has since removed; a default avatar means no portrait. Record past results as dated honors linked to their source. When you write about someone, cite their person sources in that section: the page draws its faces from your citations, so the people you report on are the people readers see.
Social research that improves the news
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.
- 12d ago Changed 5060d3c2d01d
- 18d ago First seen · 39 lines · 41 tokens per session scan A 8da08ea1de3e
competition-reporter is a skill published in the GitHub repository 82deutschmark/arc-explainer (12 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 867 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
arc-skill
Solve an interactive hidden-rule ARC-AGI-3 game from its game ID. Contains the complete playing doctrine (predict before every action, graded claims, one-page notes, optional executable-rules search) plus the arc harness the agent drives. Use whenever asked to solve, play, or continue an ARC-AGI-3 game.
unity-pipeline
Drive a running Unity Editor or development Player from the command line via the unity-pipeline package — install the package, keep the editor ticking while unfocused, run the edit→recompile→runtests loop, evaluate C#, and hot-reload files at runtime. Use when an agent needs to control a live Unity instance, automate…
anti-cheat-systems
Analyze layered anti-cheat architecture, detection evidence, telemetry, and enforcement tradeoffs. Use for system-level defense questions; use narrower skills for DMA, kernel, graphics, mobile, or server details.
dma-attack-techniques
Analyze PCIe DMA threats, host-mediated memory acquisition, FPGA behavior, and IOMMU defenses. Use when the memory initiator or device boundary matters; use kernel security for host-only mechanisms.
game-craft
A game-design guide for planning interactive games and stories. It covers player choices, recurring play, characters, world rules, state, consequences, and pacing without executing game turns or changing files.
graphics-api-hooking
Analyze Direct3D, DXGI, OpenGL, or Vulkan rendering, overlays, presentation, capture, and measurement evidence. Use when the graphics pipeline or frame-observation boundary is central.