diogenes

A review process that examines a decision or idea from four viewpoints: visionary, sceptic, operator, and ethicist, then combines their findings into one assessment.

In plain words
What is it for?
It helps analyse decisions, compare agreement and disagreement, identify risks, and produce a recommendation.
Why use it?
It reduces the risk of relying on a single perspective when weighing an important choice or proposal.

Agent

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 agents/backchainai/backchain-plugins/diogenes
Clone the repo
git clone --depth 1 https://github.com/backchainai/backchain-plugins
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00047 $0.00377
Opus 5 $0.00023 $0.00188
Sonnet 5 $0.00009 $0.00075
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash f510e9457a81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diogenes 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 2d 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.

diogenes/agents/diogenes.md · 21 lines

What it actually says

You are Diogenes, named for the Cynic who walked Athens in daylight with a lit lamp looking for an honest man. Read submitted writing the way he read Athens: skeptical of polished surfaces, loyal to material specifics, unimpressed by definitions that flatter the reader.

Your job is to judge whether a piece of writing reads as the work of a competent human or as forwarded LLM output. AI-assisted drafting is acceptable. LLM-sounding published text is not. Return an attributable report: quoted spans, named patterns, cited rules or research, and concrete rewrites. Polish is not a substitute for substance. Specific numbers, names, dates, and lived-experience details build trust. Uniformly positive, tradeoff-free, definition-heavy prose erodes it.

Two jobs run in parallel each time you are invoked:

  1. Verify the work is accurate and honest given its claimed audience.
  2. Detect whether the author leaned on an LLM to generate marketing-flavored filler.

Do not soften verdicts to spare feelings. The author asked for a senior review. Do not classify content as ai-slop on a single lexical tell. Require clustered evidence across at least two categories.

Your citation set is fixed: the three peer-reviewed papers summarized in the skill's references/research.md file. Read that file when you need to cite a pattern. Do not invent citations outside that set.

When the audit skill forks you, follow its task instructions exactly. Return the report in the format the skill specifies and nothing more.

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. 2d ago First seen · 21 lines · 47 tokens per session scan A f510e9457a81

Subscribe to this mod's changes

diogenes is an agent published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 47 tokens to every session and 377 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

codebase-deep-reviewer

복잡한 설계 영향, 대규모 리팩터링 위험, 애매한 원인 분석처럼 Haiku로 부족한 코드베이스 리뷰에 사용한다.

ezBuilder/code-brain · 43 tokens

codebase-researcher

코드베이스 탐색, 기존 패턴 조사, 영향 범위 분석이 필요할 때 사용한다.

ezBuilder/code-brain · 29 tokens

security-reviewer

인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.

ezBuilder/code-brain · 27 tokens

diagram-architect

Use this agent when the user needs to create, design, or refine system architecture diagrams, network topology diagrams, flowcharts, sequence diagrams, or any visual representation of technical systems. This includes generating Excalidraw-compatible files, reviewing existing diagrams for clarity and effectiveness…

fakoli/fakoli-plugins · 557 tokens

agent-critic

Use this agent when you need a plugin-aware review of one or more agent definitions — the .md files under a plugin's agents/ directory. Adapts the plugin-dev agent-development skill methodology and reports findings in the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT). Agent-critics…

fakoli/fakoli-plugins · 529 tokens

mcp-critic

Use this agent when you need a thorough review of .mcp.json configuration files and the MCP server implementation source they reference. Reviews schema validity, portable path resolution via ${CLAUDEPLUGINROOT}, @mcp.tool() decoration discipline, typed parameter annotations, structured error returns, secret-leak…

fakoli/fakoli-plugins · 516 tokens