Coral is a local application that gives AI agents one SQL interface for querying connected APIs, files, and live data sources. It is for agents and developers who need to retrieve and correlate data across sources while reducing repeated tool calls, pagination, and source-specific integration code. Coral exposes its query interface to compatible agents through MCP, and the catalogue add-ons support using it in agent workflows.
Borrowing it
Nothing to install: this file belongs to withcoral/coral. 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/withcoral/coral/main/.agents/skills/to-benchmark/SKILL.mdgit clone --depth 1 https://github.com/withcoral/coralWrote 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/withcoral/coral/to-benchmark)<a href="https://agentmods.dev/skills/withcoral/coral/to-benchmark"><img src="https://agentmods.dev/badge/skills/withcoral/coral/to-benchmark/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/withcoral/coral/to-benchmark"><img src="https://agentmods.dev/badge/skills/withcoral/coral/to-benchmark.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 | $0.00033 | $0.01166 |
| Opus 5.5 | $0.00013 | $0.00466 |
| Sonnet 5.5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
to-benchmark 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 8d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To Benchmark
Purpose
Create a benchmark skill for one issue. The benchmark skill runs coding agents headlessly against builds of Coral and reports whether the behaviour described in the issue improved.
Input
An issue. Any of the following counts:
- A GitHub or Linear issue reference, passed as the argument.
- A spec file path, passed as the argument.
- The current conversation, when no argument is given.
Output
A new directory .agents/benchmark-skills/bench-<behaviour>/ containing:
SKILL.md, produced by filling in TEMPLATE.md.results.jsonl, empty. The benchmark skill appends one line per run and it is committed. Run output itself goes undertasks/benchmarks/, which git ignores, and is never committed.run.py, a copy of run.py. The benchmark skill runs it once per repeat, and again to read each run's standard metrics. Edit the copy if an agent needs different flags.plot.py, a copy of plot.py. The benchmark skill runs it to writeplots.pngfromresults.jsonl. Edit the copy if the benchmark needs a different plot.
Claude Code and Codex runs load the arm's Coral plugin (plugins/coral, which holds the Coral skill), because users run agents with it installed and a branch may change it. OpenCode runs do not load the plugin, so they cannot measure changes made in the Coral skill. Users who connect only the MCP server never see the skill, so when a change targets agent behaviour, run each agent in two setups: with --coral-plugin and without it.
Procedure
-
Obtain the issue text.
- If a reference was passed, fetch the full body and all comments.
- If no reference was passed, use the conversation.
- If neither describes an agent behaviour, ask the user for the issue.
-
Write the task prompt.
- The task prompt is the message a user would have sent that leads an agent into the behaviour the issue describes.
- Write it as a user would write it. Do not describe the failure or how to avoid it.
- Agents run with their default tools, so the prompt alone has to lead them to Coral and into the behaviour. When a smoke run shows an agent answering another way, or never showing the behaviour, the benchmark skill reports back with a revised prompt; expect to revise.
- Each run produces its own failure. Runs are expected to fail in different ways. The repeat count accounts for this.
- If it is unclear what request leads to the behaviour, or more than one plausible request exists, ask the user before continuing.
What ships with it
5 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.
- 8d ago First seen · 75 lines · 33 tokens per session scan A 51b34810a53d
to-benchmark is a skill published in the GitHub repository withcoral/coral (4,938 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 1,166 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 2026-10-13.
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.