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 drn/dots --skill contestgit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/contest)<a href="https://agentmods.dev/skills/drn/dots/contest"><img src="https://agentmods.dev/badge/skills/drn/dots/contest/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/drn/dots/contest"><img src="https://agentmods.dev/badge/skills/drn/dots/contest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 210 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 211 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 212 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00026 | $0.02520 |
| Opus 5.5 | $0.00010 | $0.01008 |
| Sonnet 5.5 | $0.00005 | $0.00504 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
contest 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.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competing Implementations
Spawn multiple implementers to build different solutions to the same problem. A judge evaluates and picks the best one.
Prerequisites
Agent teams must be enabled in Claude Code settings:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
If agent teams are not enabled, report: "Agent teams required. Add CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 to your Claude Code settings (env section)." and stop.
Arguments
$ARGUMENTS- Required: the problem to solve, ideally with evaluation criteria (e.g., "optimize the search function -- prioritize readability over raw speed")
If no arguments are provided, ask the user what they want implemented.
Context
- Current branch: !
git branch --show-current - Git status: !
git status --short - Base ref: !
git branch -r 2>/dev/null | grep -oE 'origin/(main|master)' | head -1 - Project root: !
pwd - Project type: !
find . -maxdepth 1 \( -name go.mod -o -name Gemfile -o -name package.json -o -name Cargo.toml -o -name pyproject.toml -o -name setup.py -o -name requirements.txt -o -name pom.xml -o -name build.gradle -o -name Makefile \) 2>/dev/null | head -5 - Recent commits: !
git log --oneline -5 - Test files: !
find . -maxdepth 4 -name "*_test.*" -o -name "*.test.*" -o -name "*_spec.*" 2>/dev/null | head -10
Overview
You are the contest coordinator. Your job is to frame the problem, assign it to multiple implementers working in separate worktrees, and have a judge pick the winner.
Problem: $ARGUMENTS
You do NOT implement or judge yourself. You coordinate the contest.
Why this works: For design problems with multiple valid solutions (performance optimization, API design, architecture choices), building 2-3 options and comparing is faster and more reliable than debating hypothetical trade-offs.
Phase 0: Setup
-
Clean working tree: If there are uncommitted changes, commit them with message
"WIP: pre-contest state"before proceeding. -
Analyze the problem and define evaluation criteria. If the user didn't specify criteria, propose them:
- Correctness (tests pass)
- Readability / maintainability
- Performance (if relevant)
- Simplicity (fewer lines, fewer dependencies)
- Consistency with existing codebase
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 · 329 lines · 26 tokens per session scan A ab60e257c2f7
contest is a skill published in the GitHub repository drn/dots (23 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 2,520 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.