vedix-experiment-runner

vedix-experiment-runner is an agent for coding agents from danilkotelnikov/vedix. It costs 44 tokens per session (723 once invoked), scanned A, original, MIT.

A runner for Python experiments that installs the listed packages, runs the experiment, and reports the results or errors.

In plain words
What is it for?
Use it to run an experiment.py script in its own virtual environment, enforce a time limit, inspect output files, and produce a structured run report.
Why use it?
It removes the repetitive setup and debugging work when an experiment fails. It can make limited fixes based on common error messages and retry.

Agent

Part of the vedix plugin — 1 skill, 6 commands, 17 agents, 4 hooks, 10 MCP servers shipped together

Install

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.

agentmods
npx agentmods add agents/danilkotelnikov/vedix/experiment-runner
Clone the repo
git clone --depth 1 https://github.com/danilkotelnikov/vedix

Or install vedix, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 17 agents, 4 hooks, 10 MCP servers.

Wrote 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.

agentmods badge for vedix-experiment-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/danilkotelnikov/vedix/experiment-runner.svg)](https://agentmods.dev/agents/danilkotelnikov/vedix/experiment-runner)
Your own site
<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/experiment-runner"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/experiment-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00723
Opus 5 $0.00022 $0.00362
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00004 $0.00072

Measured 3d ago against content hash 534960079f81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vedix-experiment-runner 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 3d 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.

plugins/vedix/agents/experiment-runner.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Runner

Install deps, run, retry on failure with surgical patches.

Inputs

  • <input name="output_dir"> — has experiment.py, requirements.txt, .venv/
  • <input name="auto_fix_max_rounds"> — default 3
  • <input name="timeout_seconds"> — default 300

Steps

  1. Install: cd <output_dir> && .venv\Scripts\pip install -r requirements.txt (Unix: .venv/bin/pip). Capture stderr.

  2. Run: cd <output_dir> && .venv\Scripts\python experiment.py > experiment_stdout.txt 2> experiment_stderr.txt with timeout=<timeout_seconds>.

  3. Evaluate:

    • exit 0 → done. Read results.csv, list .npy/figures/.
    • exit ≠ 0 → parse stderr, classify error type, apply minimal fix:
Error class Detection Typical fix
ImportError ModuleNotFoundError, No module named Add missing package to requirements.txt and reinstall
SyntaxError SyntaxError Fix the specific line cited in stderr
NameError NameError: name 'X' is not defined Fix the reference (typo or missing import)
FileNotFoundError FileNotFoundError Create the file or fix the path
TypeError/ValueError mismatched arguments, bad cast Wrap in try/except or fix the logic
Timeout exceeded timeout_seconds Simplify computation, reduce data size, retry
  1. Re-run with same command. Up to auto_fix_max_rounds rounds total.

  2. Log fixes to experiment_fix_log.json:

[
  {
    "attempt": 1,
    "error_type": "ImportError",
    "error_message": "No module named 'networkx'",
    "fix_applied": "Added networkx to requirements.txt and reinstalled",
    "re_run_exit_code": 0
  }
]
  1. After exhaustion, return whatever state exists (do NOT silently proceed if final exit ≠ 0 — let orchestrator's Fixer flow take over).

Output

<output name="run_report">
{
  "final_exit_code": 0,
  "fix_attempts": 1,
  "stdout_summary": "...",
  "stderr_summary": "...",
  "results_csv_present": true,
  "npy_files": [],
  "figures": [],
  "fix_log": []
}
</output>

Read the full file on GitHub · 87 lines

Changes

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.

  1. 3d ago First seen · 87 lines · 44 tokens per session scan A 534960079f81

Subscribe to this mod's changes

vedix-experiment-runner is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 723 once invoked, about $0.0002 per session on Opus 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.

Related

Other agents, from other repositories

coder

Specialized sub-agent for the AI co-mathematician system. Implements Python code for computational exploration, numerical verification, and search — with mandatory tests and golden values. Cannot mark its work complete until tests pass and a reviewer accepts the golden values. Use when the project-coordinator…

morankor/theorist-toolbox · 78 tokens

wtfp-outliner

Turn the approved project brief into the structural foundation for an academic document. The role defines what each section must accomplish, how claims depend on one another, where evidence is needed, and which sections can be developed concurrently.

akougkas/wtf-p · 48 tokens

wtfp-section-writer

Execute an approved section plan into evidence-grounded academic prose or the explicitly requested scaffold. Preserve the author’s epistemic authority, make only supported claims, and leave an auditable account of what was produced and what remains unresolved.

akougkas/wtf-p · 51 tokens

wtfp-section-reviewer

Review a section as an academic evaluator and produce prioritized, actionable feedback. The invocation may select a review lens—adversarial peer, significance-focused chair, production editor, or constructive mentor—without changing the underlying evidence standard.

akougkas/wtf-p · 51 tokens

atlas-data-plotter

Use this agent when a user requests Python code to access ATLAS data, extract specific items, and generate plots. The agent will run the generated script with nfiles=1 to make sure it compiles and generates output. The results will be best if the agent can star with a specification generated by the…

iris-hep/marketplace · 461 tokens

ReviewerAgent

MUST BE USED. Deeply and critically inspect the project from scientific views, just like human reviewers for high impact journals.

scitex-ai/scitex-python · 28 tokens