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.
npx agentmods add skills/haabe/mycelium/devils-advocatenpx skills add haabe/mycelium --skill devils-advocategit clone --depth 1 https://github.com/haabe/myceliumWrote 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/skills/haabe/mycelium/devils-advocate)<a href="https://agentmods.dev/skills/haabe/mycelium/devils-advocate"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/devils-advocate.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 | $0.00027 | $0.02573 |
| Opus 5 | $0.00014 | $0.01287 |
| Sonnet 5 | $0.00005 | $0.00515 |
| Haiku 4.5 | $0.00003 | $0.00257 |
Grade A, and why
devils-advocate 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 today.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate
Run before every major diamond transition and architecture decision. Source: Kahneman, Shotton.
Technique 1: Pre-Mortem
Imagine it's 6 months from now and this decision FAILED spectacularly.
- What went wrong?
- What assumption was the weakest link?
- What signal did we ignore?
- Who was affected and how?
Technique 2: Assumption Reversal
For each key assumption:
- State the assumption explicitly
- Ask: "What if the OPPOSITE is true?"
- What evidence would support the opposite?
- Is there any evidence we've dismissed?
Technique 3: Red Team
Attack your own position:
- What would a competitor say about this approach?
- What would a skeptical user say?
- What would a security auditor find?
- What would an accessibility advocate flag?
10 Challenge Questions
- What are we most confident about? (That's where overconfidence hides)
- What evidence have we dismissed or downweighted?
- Are we anchored on our first idea? (Shotton - anchoring bias)
- Have we tested with users who DON'T match our ideal profile?
- What would make us abandon this direction entirely?
- Are we building for ourselves or for actual users?
- What's the simplest version that could validate/invalidate this?
- What have we NOT measured that we should?
- If we had to start over, would we make the same choice?
- Who disagrees with us and what's their strongest argument?
Technique 4: Attribution-vs-Consistency Check
Per anti-pattern Consistency-as-Evidence (#7) — graduated 2026-05-09 from a recurring failure where causal chains were built from observational consistency rather than verified attribution.
For each piece of evidence supporting the current claim, label it:
- Cleanly-attributed: the cause was demonstrably driving the effect (the action was Mycelium-specific, the variable was isolated, the alternative explanations were ruled out).
- Consistency-only: the data is compatible with the hypothesis but doesn't isolate the cause (the user reported X in a context where Y was also true; the trend matches the prediction but matches three other predictions equally well).
- Unrelated: the evidence is a different question entirely; don't include it in the chain.
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.
- today Changed · +2 lines 651da22cec45
- 4d ago First seen · 122 lines · 27 tokens per session scan A 97c404fce8d6
devils-advocate is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,573 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.
Other skills, from other repositories
cto-orchestration
CTO/orchestrator 模式管理多 agent 软件交付：agentctl 统一派工（一条 duplex lane、三引擎原生协议，轮内 steer）、goal 合同驱动、typed watcher、异构评审、真路径验收与主理人减负。适用于用户要求'你做 CTO/编排者'、'派 omp/codex 去做'、'goal 模式派发'、管理多会话开发或把这套工作流接入新项目；用户说'复盘 / 收口 / retro / retrospective'时也必须触发（七步仪式 + retro-check 硬门），说'工作盘点 / 盘点候选 / stocktake'时同样触发（盘点仪式，只提案不动工）。新项目先用…
observability-standard
生产级可观测性规范,所有后端服务通用(普通微服务与 agent / 多 agent / RAG 项目;Python / Go / Java / Rust)。核心:traceid 串 trace/log + 业务 id 反查 db、结构化日志、OpenTelemetry 埋点与跨进程传播、日志级别与边界类型纪律;agent / RAG 在此基线上加 LLM / 工具 / 检索埋点(GenAI 语义约定)。Use whenever writing or reviewing backend code involving logging, tracing, structured logs, context propagation, log…
orchestrator-core
多智能体编排的领域无关内核（A² Supervisor 层的方法论抽象）。把编排者的操作系统从领域里剥出来：萃取式主上下文 + 按『要不要主上下文』切分派工 + 契约化派发 + 分层合并 + 对抗式异构验证 + 降认知负载。领域皮（CTO 写码 / 总编内容 / 未来任意领域）只贴一张薄角色表 + 完成定义，内核整套复用。适用于用户要求抽象编排模式、造新领域编排者、或问『多智能体架构怎么搭』。不要用于：单 agent 一次性小任务（无需内核）、纯文档初始化（用 repo-governance-bootstrap）。派工/评审/状态落盘的领域实现见各皮 skill（cto-orchestration / yangge-ops）。.
agent-backend-standard
生产级 agent 时代后端工程手册(hub)——建 / 评审 agent·LLM 后端、任何碰 DB 的持久层后端、或为任何后端建立 / 评审 repo 工程门禁时加载。覆盖架构、prompt、工具(ACI)、记忆、检索/RAG、韧性幂等、人在环、安全护栏与有界执行、评估、成本、依赖生命周期,及数据访问 / 缓存 / 秘密接触面三纪律与 Python/Go/Java/Rust 统一 fix/check/test 门禁。本文件是目录,深度按需读 references/;可观测性/Git/A2A 是独立 skill,本 hub 只交叉引用。Use when building or reviewing agent/LLM…
agent-frontend-standard
Skill "agent-frontend-standard" from martin1847/evolab, covering agent frontend — 前端工程手册, 1. 设计系统即 agent 契约, 2. 类型端到端契约, 3. 视觉验证环 and 4. 测试分时门禁.
git-workflow-standard
生产级 Git 协作 SOP:受保护分支按仓库 tier 门禁、改动从 feature 分支起、集成默认 squash、rebase 判据、提交不加 AI 签名。任何 git commit / push / 开 PR / 建分支 / rebase / 合并场景加载;agent 写完代码准备提交前必读。Use when committing, pushing, opening a PR, branching, rebasing, or merging.