full_study

full_study is a command for Claude Code from swarm-ai-research/swarm. It costs 0 tokens per session (3,325 once invoked), scanned A, original, MIT.

An end-to-end research workflow for running experiments and preparing a paper draft. It can sweep parameter choices, analyze results statistically, create plots, and assemble the draft.

In plain words
What is it for?
Use it for simulation studies or detection experiments, parameter sweeps, seed-based comparisons, result plots, and initial paper scaffolding.
Why use it?
It connects repeated experiments and their analysis into one process, reducing manual handoffs between research tasks.

Command for Claude Code

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 commands/swarm-ai-research/swarm/full_study
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

Made for: Claude Code.

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 full_study

README.md
[![agentmods](https://agentmods.dev/badge/commands/swarm-ai-research/swarm/full_study.svg)](https://agentmods.dev/commands/swarm-ai-research/swarm/full_study)
Your own site
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/full_study"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/full_study.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,325 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 $0.00000 $0.03325
Opus 5 $0.00000 $0.01663
Sonnet 5 $0.00000 $0.00665
Haiku 4.5 $0.00000 $0.00332

Measured 5d ago against content hash 1018c7d7bdc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

full_study 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.

.claude/commands/full_study.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/full_study

End-to-end research pipeline: sweep parameters, analyze with statistical rigor, generate plots, and scaffold a paper draft. Chains /sweep, /analyze_experiment, /plot, and /write_paper into a single workflow.

Usage

/full_study <scenario_path> [title_slug] [--seeds N] [--params key=val1,val2 ...] [--refine [--depth lite|full]]

/full_study --detection [title_slug] [--seeds N] [--agents N] (detection-experiment mode; no scenario)

Examples:

  • /full_study scenarios/rlm_recursive_collusion.yaml collusion_tax_effect
  • /full_study scenarios/kernel_market/baseline.yaml kernel_governance --seeds 10
  • /full_study scenarios/baseline.yaml governance_sweep --seeds 5 --params governance.transaction_tax_rate=0.0,0.05,0.1,0.15 --params governance.circuit_breaker_enabled=True,False
  • /full_study --detection soft_vs_binary_detection --seeds 10

Arguments

  • scenario_path: Path to the scenario YAML file. Omit (and pass --detection) for detection-experiment mode.
  • title_slug (optional): Slug for the paper filename. Default: derived from scenario_id (or soft_vs_binary_detection in --detection mode).
  • --seeds N: Number of seeds per configuration. Default: 10.
  • --params: Parameter sweep axes, passed through to the sweep step. If omitted, uses the default sweep in examples/parameter_sweep.py. (Ignored in --detection mode.)
  • --detection: Run the matched soft-vs-binary detection experiment instead of a scenario sweep (see "Detection mode" below). Phase 1 runs experiments/run_detection_experiment.py; Phases 2–4 consume its summary.json.
  • --agents N: (detection mode only) Agents per population. Default: 40.
  • --refine: After the paper draft, run the AgentLab refinement pipeline (see Phase 4b below). Optional.
  • --depth lite|full: Refinement depth (only used with --refine). Default: lite.

Behavior

Detection mode (--detection) replaces the scenario-sweep pipeline with the matched soft-vs-binary detection experiment. The phase structure is preserved so the rest of the pipeline (analysis, plots, paper, summary) works unchanged — only the data source differs. Where a phase below says "in detection mode", follow that branch. The remaining phases (2b council, 4b refinement, 5 summary) work identically, reading summary.json from the detection run dir.

Read the full file on GitHub · 273 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 · 273 lines · 0 tokens per session scan A 1018c7d7bdc4

Subscribe to this mod's changes

full_study is a command published in the GitHub repository swarm-ai-research/swarm (41 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,325 tokens. 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 2026-08-30.