vedix-tree-search-runner

vedix-tree-search-runner is an agent for Claude Code from danilkotelnikov/vedix. It costs 103 tokens per session (1,421 once invoked), scanned A, original, MIT.

An experiment runner that explores several possible implementations in a best-first tree search, a method that expands the most promising option first, and chooses the best result by a defined metric.

In plain words
What is it for?
Use it when an experiment.py seed implementation has several plausible versions and you want parallel evaluation within a time budget.
Why use it?
It addresses experiments where the correct algorithm or implementation is unclear in advance. It searches beyond one script and compares multiple variants, though it takes longer than a single run.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Codex.

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/tree-search-runner
Clone the repo
git clone --depth 1 https://github.com/danilkotelnikov/vedix

Made for: Claude Code.

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-tree-search-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/danilkotelnikov/vedix/tree-search-runner.svg)](https://agentmods.dev/agents/danilkotelnikov/vedix/tree-search-runner)
Your own site
<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/tree-search-runner"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/tree-search-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,421 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 5.1 $0.00103 $0.01421
Opus 5 $0.00051 $0.00711
Sonnet 5 $0.00021 $0.00284
Haiku 4.5 $0.00010 $0.00142

Measured 5d ago against content hash 54e7ebc0931c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vedix-tree-search-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 5d 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/tree-search-runner.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tree-Search Experiment Runner (BFTS)

Replaces the single-shot experiment-runner agent for runs invoked with --bfts. Uses canonical Sakana's Best-First Tree Search to explore the space of possible implementations of the hypothesis's experiment, parallel-evaluate them, and pick the best.

When the orchestrator dispatches this agent

  • User passes --bfts flag to /vedix
  • Or settings has experiment.use_bfts: true
  • Or the topic is flagged as "implementation-uncertain" (multiple plausible algorithms)

The default experiment-runner is faster (single-shot + auto-fix), but BFTS produces materially better results when the right implementation is unclear up-front.

Inputs

  • <input name="output_dir"> — has experiment.py (seed implementation) + requirements.txt + .venv/
  • <input name="hypothesis_md"> — full hypothesis text
  • <input name="bfts_config_path"> — path to bfts_config.yaml (default: <plugin>/mcp/lib/sakana/bfts_config.yaml)
  • <input name="time_budget_minutes"> — total wall-clock budget (default 30)
  • <input name="palace_path"><output_dir>/.palace

Universal MemPalace contract

mcp__mempalace__wake_up(root="<palace_path>", token_budget=2000)

on entry — load any prior tree-search snapshots from earlier runs of this project.

mcp__mempalace__mine(
  root="<palace_path>",
  content="<best variant + tree summary + losses>",
  tags=["vedix", "phase:4-bfts", "agent:tree-search-runner", "best_metric:<value>"]
)

on exit.

Steps

  1. Read <plugin>/mcp/lib/sakana/bfts_config.yaml. Note the defaults: num_workers, max_depth, time_budget, eval_metric. If the user passed overrides via flags, write a per-job config to <output_dir>/bfts_config.yaml with the overrides applied.

  2. Read experiment.py from output_dir as the seed/root node of the tree.

  3. Invoke BFTS via Bash:

    cd <output_dir> && \
    .venv/Scripts/python <plugin>/mcp/lib/sakana/treesearch/perform_experiments_bfts_with_agentmanager.py \
      --config <output_dir>/bfts_config.yaml \
      --workspace <output_dir> \
      --hypothesis <output_dir>/hypothesis.md \
      --seed-experiment <output_dir>/experiment.py \
      --time-budget-minutes <time_budget_minutes> \
      2>&1 | tee <output_dir>/bfts_log.txt
    

Read the full file on GitHub · 130 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. 5d ago First seen · 130 lines · 103 tokens per session scan A 54e7ebc0931c

Subscribe to this mod's changes

vedix-tree-search-runner is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 103 tokens to every session and 1,421 once invoked, about $0.0005 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

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-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

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

compact

You are an ultrarunning training companion. Read SOUL.md at the start of the session for your name and voice, then read athlete/profile.md and athlete/notes.md. Walk beside the athlete: explain options and tradeoffs, and leave the decision with them.

rlacombe/switchback-running · 0 tokens

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens