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/plot.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/plot)<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/plot"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/plot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/plot"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/plot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00472 |
| Opus 5.5 | $0.00000 | $0.00189 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
plot 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 1mo 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.
What it actually says
/plot
Generate standard plots from a previously-exported run folder.
Usage
/plot <run_dir> [metric]
Examples:
/plot runs/20260208-120102_baseline_seed42/plot runs/20260208-120102_baseline_seed42 toxicity_rate
Inputs (expected)
<run_dir>/history.json(frompython -m swarm run ... --export-json ...) or<run_dir>/csv/(from--export-csv)
Outputs
Write plots under:
<run_dir>/plots/
At minimum generate:
- Time series: toxicity, quality_gap, welfare
- Acceptance rate over time (if available)
If optional deps are missing (e.g. swarm-safety[analysis]), fall back to:
- Writing
<run_dir>/plots/README.txtwith install instructions and what would be plotted.
Sweep data detection
If the input path points to a sweep CSV (contains columns like governance.* or multiple run_index values), generate sweep-specific plots instead of time-series plots:
- Grouped bar charts: welfare and toxicity by each swept parameter, with individual data points overlaid and ±1 SD error bars
- Box plots: welfare distribution per configuration
- Heatmap: mean welfare/toxicity/quality_gap across the parameter grid (if 2 swept parameters)
- Agent payoff comparison: honest/opportunistic/adversarial payoffs by config
- Effect size plot: governance lever boost with 95% CI and significance annotations
Detect sweep data by checking for:
- Multiple unique values in columns matching
governance.* - A
run_indexcolumn with values > 0 - No
epochcolumn (sweep CSVs aggregate across epochs)
Concrete implementation
For single-run time-series data:
python examples/plot_run.py <run_dir> [--metric <metric>]
For sweep data:
python examples/plot_sweep.py <csv_path> [--output-dir <dir>]
The sweep script auto-detects governance.* columns with multiple unique values and generates the 6 standard plot types listed above.
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.
- 1mo ago First seen · 57 lines · 0 tokens per session scan A eab486cde6e0
plot is a command published in the GitHub repository swarm-ai-research/swarm (48 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 472 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
story-long-scan
A command for scanning long-form online fiction rankings on platforms such as Qidian, Fanqie, and Jinjiang, then analyzing the ranking data.
story-short-scan
A tool for scanning and analysing popular short web-fiction rankings on platforms such as Zhihu Yanyan and Fanqie Short Stories.
setup
Configure MeiGen MCP credentials privately, or set up an OpenAI-compatible provider for ordinary image generation. Use for /meigen:setup, "configure meigen", "add API key", or connection setup requests.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
reflect
Curate and compress recent memory. This command reviews the last 7 days of journal entries, extracts durable insights, and updates long-term memory files. Think of it as memory maintenance -- moving important things from short-term to long-term storage.