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 agentmods add agents/danilkotelnikov/vedix/experiment-runnergit clone --depth 1 https://github.com/danilkotelnikov/vedixWrote 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/agents/danilkotelnikov/vedix/experiment-runner)<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>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 | $0.00044 | $0.00723 |
| Opus 5 | $0.00022 | $0.00362 |
| Sonnet 5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
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.
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">— hasexperiment.py,requirements.txt,.venv/<input name="auto_fix_max_rounds">— default 3<input name="timeout_seconds">— default 300
Steps
-
Install:
cd <output_dir> && .venv\Scripts\pip install -r requirements.txt(Unix:.venv/bin/pip). Capture stderr. -
Run:
cd <output_dir> && .venv\Scripts\python experiment.py > experiment_stdout.txt 2> experiment_stderr.txtwith timeout=<timeout_seconds>. -
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 |
-
Re-run with same command. Up to
auto_fix_max_roundsrounds total. -
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
}
]
- 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>
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.
- 3d ago First seen · 87 lines · 44 tokens per session scan A 534960079f81
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.
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…
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.
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.
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.
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…
ReviewerAgent
MUST BE USED. Deeply and critically inspect the project from scientific views, just like human reviewers for high impact journals.