Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ihsaan-ullah/auto-codabenchnpx agentmods add skills/ihsaan-ullah/auto-codabench/codabench-bundleWrote 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/ihsaan-ullah/auto-codabench/codabench-bundle)<a href="https://agentmods.dev/skills/ihsaan-ullah/auto-codabench/codabench-bundle"><img src="https://agentmods.dev/badge/skills/ihsaan-ullah/auto-codabench/codabench-bundle/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/ihsaan-ullah/auto-codabench/codabench-bundle"><img src="https://agentmods.dev/badge/skills/ihsaan-ullah/auto-codabench/codabench-bundle.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 | $0.00051 | $0.08208 |
| Opus 5.5 | $0.00020 | $0.03283 |
| Sonnet 5.5 | $0.00010 | $0.01642 |
| Haiku 4.5 | $0.00005 | $0.00821 |
Grade A, and why
codabench-bundle 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 — 864 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codabench Bundle: Technical Reference
This skill is the schema-level reference for generating a Codabench
competition bundle on disk. It only covers what is needed to produce a
lint-clean, upload-ready .zip. Compute-worker setup, Docker image
building, and server administration are explicitly out of scope.
A Codabench competition bundle is a zip file containing a top-level
competition.yaml plus the assets it references. The platform unpacks
the zip server-side; everything the bundle declares must resolve to a
file path relative to competition.yaml.
Set version: 2 at the top of every new bundle. v1 and v1.5 are legacy.
1. Bundle directory layout
The structure below is the canonical layout. Filenames are flexible —
what matters is that they match the paths referenced from
competition.yaml.
my_competition/ # the directory you will zip the CONTENTS of
├── competition.yaml # required, at the root of the zip
├── logo.png # competition logo, referenced by `image:`
├── pages/ # markdown/HTML pages shown as tabs
│ ├── overview.md # conventional landing tab
│ ├── evaluation.md # how submissions are scored
│ ├── terms.md # T&Cs (also referenced by `terms:`)
│ ├── data.md # data description
│ └── starting_kit.md # (optional) link to / describe the starter
├── scoring_program/ # required by every task
│ ├── metadata.yaml # has a `command:` key, see §7
│ ├── scoring.py # or any executable referenced by command
│ └── ... # helper modules, requirements, etc.
├── ingestion_program/ # required only for code-submission tasks
│ ├── metadata.yaml # has a `command:` key, see §8
│ └── ingestion.py
├── input_data/ # data used by ingestion program/prediction step
│ └── ... # mounted at /app/input_data on the worker
├── reference_data/ # ground truth, only the scoring program sees it
│ └── truth.csv # mounted at /app/input/ref
├── solutions/ # example/baseline submissions
│ ├── solution1.zip
│ └── solution2/
├── starting_kit/ # (optional) downloadable starter for participants
│ └── ...
└── public_data/ # (optional) downloadable public data
└── ...
What ships with it
4 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 · 864 lines · 51 tokens per session scan A 9397fdb7226c
codabench-bundle is a skill published in the GitHub repository ihsaan-ullah/auto-codabench (2 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 8,208 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…