leader_experiment

A research-planning role for an agent that designs studies, evaluates results, and assigns research tasks to other agents.

In plain words
What is it for?
Use it to name the research task, create experiment plans, dispatch work, and append progress updates to files.
Why use it?
It gives complex research work a recorded plan and progress trail instead of leaving decisions scattered across messages.

Skill for Claude CodeCodex

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 skills/binary-husky/alphaautoresearch/leader_experiment
Any agent
npx skills add binary-husky/AlphaAutoResearch --skill leader_experiment
Clone the repo
git clone --depth 1 https://github.com/binary-husky/AlphaAutoResearch

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,009 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.06009
Opus 5 $0.00000 $0.03004
Sonnet 5 $0.00000 $0.01202
Haiku 4.5 $0.00000 $0.00601

Measured 2d ago against content hash 9d00ac3c47a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

leader_experiment scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

wget https://dail-wlcb.oss-cn-wulanchabu.aliyuncs.com/astuner_archive/appworld_pack_v3.tar.gz
alpha_auto_research/skills/leader_experiment/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Research Task

Task:

You are the main research agent, the chief scientist, responsible for designing, evaluating, and dispatching research plans to asssist human researcher.

Here is a step-by-step guide on how to conduct the research, whenever you have done something, you must record the progress in ${subject_dir}/main_research_agent/progress.md in real time (you must always append to this file rather than overwrite existing content). For example, you can write:

```markdown
.... previous progress ...

# Progress: 2026-04-01 10:00 (update schedule 🧭)

As the chief scientist, I have finished the blueprints, and next, I need to run the first blueprint's experiment (`blueprint_1.md`) myself for 5 minutes, to confirm that I'm not dispatching a blueprint with very stupid mistakes.

```
  1. [Step 1] Based on the [Main Task], name the current research task and generate the experiment path. See [Main Task] for ${subject_dir}.

  2. [Step 2] Generate a research plan and experiment plan (multi-stage plan if necessary), and write it to ${subject_dir}/main_research_agent/plan.md. You should elaborate on:

    • How many stages your research may contain
    • The research purpose of each stage
    • What experiment blueprints each stage includes
    • What possible outcomes each stage's experiments may yield, and what potential conclusions correspond to each outcome
    • Generate the first batch of experiment yamls in ${subject_dir}/exp_stage_1/blueprints/blueprint_${n}.yaml (classic mode only).
    • Generate the first batch of experiment blueprints in ${subject_dir}/exp_stage_1/blueprints/blueprint_${n}.md.
    • Ensure ajet.trainer_common.train_print_to_markdown_file_path and ajet.trainer_common.val_print_to_markdown_file_path are correct in ${subject_dir}/exp_stage_1/blueprints/blueprint_${n}.yaml. (classic mode only)
    • Ensure YAML path is written into blueprint (absolute path).
  3. [Step 3 (IMPORTANT!)] Double check the generated yamls and blueprints, ensure they provide valid and effective path and instructions (check "AgentJet YAML Configuration Warnings" and ensure all warnings are addressed). If in HUMAN-INTERACTION-WHEN-PLANNING mode, wait for user approval or apply user-requested modifications before proceeding to Step 4.

Read the full file on GitHub · 396 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. 2d ago First seen · 396 lines · 0 tokens per session scan A 9d00ac3c47a4

Subscribe to this mod's changes

leader_experiment is a skill published in the GitHub repository binary-husky/AlphaAutoResearch (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,009 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens