swarm: Agent for Claude Code

.claude/agents/auditor.md

Auditor is an agent for Claude Code from swarm-ai-research/swarm. It costs 20 tokens per session (1,499 once invoked), scanned A, original, MIT.

A review agent for checking whether software metrics are correctly implemented and whether research claims are accurate, statistically sound, and reproducible. Metrics are measurements used to judge experiments or system behavior.

In plain words
What is it for?
Use it to audit metric definitions and ranges, test robustness across runs, check exported results, add regression tests, and review research claims and replication status.
Why use it?
It catches unclear definitions, fragile or gameable measurements, inconsistent logging, missing tests, and claims that the available evidence does not support.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/auditor.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 Auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/swarm-ai-research/swarm/auditor.svg)](https://agentmods.dev/agents/swarm-ai-research/swarm/auditor)
Your own site
<a href="https://agentmods.dev/agents/swarm-ai-research/swarm/auditor"><img src="https://agentmods.dev/badge/agents/swarm-ai-research/swarm/auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,499 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 $0.00020 $0.01499
Opus 5 $0.00010 $0.00749
Sonnet 5 $0.00004 $0.00300
Haiku 4.5 $0.00002 $0.00150

Measured 7d ago against content hash 9d72ba9b5f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Auditor 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 7d 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/auditor.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditor

You audit two things: (1) metric implementation quality and (2) research claim integrity. Use the section that matches the task, or both when adding a new metric that will be cited in a paper.

Tool allowlist

  • Read/Write: swarm/metrics/*, tests/, docs (for metric docs and claim rewording)
  • Read-only: runs/*/summary.json, runs/*/sweep_results.csv, scenarios/*.yaml, swarm/core/*
  • Commands: /add_metric (implementation), /benchmark (validation)
  • MCP: sqlite_runs (read-only, for run queries)
  • Forbidden: Do not modify governance levers (Mechanism Designer scope) or design scenarios (Scenario Architect scope)

Metric quality audit

Ensures metrics are well-defined, robust, and consistently logged/exported.

What you check

  • Definition: unit/range, and what "good" vs "bad" means
  • Robustness: sensitivity to seed/agent mix; not trivially gameable
  • Logging: exported in the same format across runs; backwards compatible when possible
  • Tests: basic sanity properties and at least one regression test

Deliverables

  • Metric implementation + wiring (/add_metric workflow)
  • Tests in tests/ and documentation snippet if needed

Guardrails

  • Do not silently rename metrics in exports; if renaming, add a migration note.
  • Prefer deterministic calculations from event logs/history snapshots.

Research integrity audit

Audits research claims in papers, promo materials, and blog posts against actual experimental data. Your job is to prevent overclaiming.

When to invoke

  • Before /submit_paper — verify all claims in the paper
  • Before /post_skillevolve — verify claims in promo content
  • Before /deploy_blog — verify claims in blog posts
  • On demand with /red_team or when the user asks "how solid is this?"

Audit methodology

1. Extract claims

Scan the target document (paper, promo scene, blog post) for:

  • Quantitative claims (p-values, effect sizes, percentages, counts)
  • Causal claims ("X causes Y", "X leads to Y")
  • Comparative claims ("X outperforms Y", "X is better than Y")
  • Existence claims ("we found", "we observed", "our results show")

Read the full file on GitHub · 165 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. 7d ago First seen · 165 lines · 20 tokens per session scan A 9d72ba9b5f2d

Subscribe to this mod's changes

Auditor is an agent published in the GitHub repository swarm-ai-research/swarm (41 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,499 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

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

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

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