Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/commands/compare_studies.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/commands/swarm-ai-research/swarm/compare_studies)<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/compare_studies"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/compare_studies.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 5.1 | $0.00000 | $0.01428 |
| Opus 5 | $0.00000 | $0.00714 |
| Sonnet 5 | $0.00000 | $0.00286 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
compare_studies 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 8d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compare_studies
Compare results across multiple completed study run directories: compute cross-study descriptive statistics, pairwise tests, and generate a comparison plot.
Usage
/compare_studies <run_dir1> <run_dir2> [run_dir3 ...] [--metric welfare] [--output <path>]
Examples:
/compare_studies runs/20260213-003757_ldt_large_population_study runs/20260213-003812_ldt_low_prior_study/compare_studies runs/*_ldt_*_study/compare_studies runs/study_a runs/study_b runs/study_c --metric toxicity_rate
Arguments
run_dir: Two or more run directories containingsweep_results.csvand/oranalysis/summary.json--metric: Primary metric for comparison (default:welfare). Also acceptstoxicity_rate,quality_gap,honest_payoff,adversarial_payoff.--output: Output directory for combined analysis and plots (default:runs/with auto-generated filename).
Behavior
Phase 1: Load and validate
For each run directory:
- Look for
sweep_results.csv— load as DataFrame - Look for
analysis/summary.json— load descriptive stats and pairwise tests - Extract the scenario name from
summary.json→scenariofield, or infer from directory name - If neither file exists, skip with a warning
Validate that all studies sweep the same parameter (e.g. all sweep acausality_depth). If parameters differ, warn but proceed (label axes accordingly).
Phase 2: Cross-study descriptive statistics
For each study, extract per-condition means and SDs for all available metrics. Produce a combined table:
| Study | Condition | Welfare (mean +/- SD) | Toxicity | Honest Payoff | Adversarial Payoff |
|----------------|-----------|----------------------|----------|---------------|--------------------|
| large_pop | depth=1 | 366.38 +/- 19.69 | 0.3425 | 22.47 | 3.34 |
| large_pop | depth=2 | 371.41 +/- 16.33 | 0.3434 | 23.41 | 3.15 |
| ... | ... | ... | ... | ... | ... |
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.
- 8d ago First seen · 127 lines · 0 tokens per session scan A a188d1d9b901
compare_studies 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 1,428 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.
Other commands, from other repositories
list-skills
List all available ClawBio bioinformatics skills with their status and capabilities.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.