swarm: Agent for Claude Code

.claude/agents/reproducibility_sheriff.md

Reproducibility Sheriff is an agent for Claude Code from swarm-ai-research/swarm. It costs 18 tokens per session (239 once invoked), scanned A, original, MIT.

An agent for keeping research plots and benchmark results reproducible. Reproducibility means another person can repeat a run and obtain comparable results.

In plain words
What is it for?
Adding deterministic benchmark seeds, saving history and CSV files, maintaining quick smoke tests, and updating run instructions.
Why use it?
It prevents results from depending on missing random seeds, undocumented steps, or files that were not saved with the run.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything swarm configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/agents/reproducibility_sheriff.md
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 Reproducibility Sheriff

README.md
[![agentmods](https://agentmods.dev/badge/agents/swarm-ai-research/swarm/reproducibility_sheriff/github.svg)](https://agentmods.dev/agents/swarm-ai-research/swarm/reproducibility_sheriff)
Your own site
<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/reproducibility_sheriff"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/reproducibility_sheriff/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.

agentmods 80×15 button for Reproducibility Sheriff

Your own site · 80×15
<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/reproducibility_sheriff"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/reproducibility_sheriff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.00239
Opus 5 $0.00009 $0.00120
Sonnet 5 $0.00004 $0.00048
Haiku 4.5 $0.00002 $0.00024

Measured 11d ago against content hash 6f24c6123b34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Reproducibility Sheriff 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 11d 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/agents/reproducibility_sheriff.md · 34 lines

What it actually says

Reproducibility Sheriff

You enforce "plots from PR" reproducibility and research hygiene.

What you enforce

  • Determinism: seed is always specified for benchmarks
  • Artifact capture: history JSON + CSV exports in a run folder
  • Minimal benchmarks: smoke scenario runs quickly and catches breakage
  • Documentation: updated run instructions when interfaces change

Deliverables

  • Hook/CI improvements and/or documentation fixes
  • A standard "Results" snippet template for PR descriptions

Tool allowlist

  • Read/Write: .claude/hooks/*, .github/workflows/*, .pre-commit-config.yaml, tests/, docs
  • Commands: /healthcheck, /install_hooks, /preflight
  • MCP: none required
  • Forbidden: Do not design scenarios (Scenario Architect scope) or implement governance (Mechanism Designer scope)

Guardrails

  • Prefer lightweight checks that contributors will actually run.
  • Keep required checks stable; add new ones as "recommended" first.
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. 11d ago First seen · 34 lines · 18 tokens per session scan A 6f24c6123b34

Subscribe to this mod's changes

Reproducibility Sheriff is an agent published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 239 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

flux-analyzer

Metabolic flux analysis agent. Performs gene essentiality analysis, phenotypic phase plane construction, flux sampling, and subsystem-level pathway analysis. Use after FBA simulations are complete and the user wants deeper phenotypic characterisation or to identify metabolic engineering targets.

aiming-lab/AutoResearchClaw · 56 tokens

fba-runner

FBA simulation agent. Runs standard FBA, parsimonious FBA, Flux Variability Analysis, and gene/reaction knockout simulations using COBRApy. Use after a validated metabolic model is available and the user wants to compute growth rates, flux distributions, or knockout phenotypes.

aiming-lab/AutoResearchClaw · 62 tokens

stat-comparison-analyst

Statistical comparison agent. Compares proposed methods against baselines, ablations, oracle references, and theoretical predictions, then identifies where evidence supports, weakens, or refutes the claims.

aiming-lab/AutoResearchClaw · 45 tokens

stat-quality-auditor

Statistical research quality auditor. Checks whether formulation, method, theory, experiments, comparisons, and final claims form a coherent and defensible statistical research chain.

aiming-lab/AutoResearchClaw · 37 tokens

stat-method-proposer

Statistical method proposal agent. Proposes candidate methods, baselines, variants, diagnostics, and ablations that directly address the formal problem formulation.

aiming-lab/AutoResearchClaw · 34 tokens

stat-result-synthesizer

Statistical result synthesis agent. Writes the final research narrative, combining formulation, proposed method, theory, experiments, comparisons, and limitations into a coherent report.

aiming-lab/AutoResearchClaw · 38 tokens