devils-advocate

devils-advocate is an agent for Claude Code from sabahudin-web/competitive-intelligence-radar. It costs 67 tokens per session (575 once invoked), scanned A, original, MIT.

A skeptical strategy analyst that tries to disprove proposed recommendations and identify unsupported or stale claims. It is one member of the radar council's four-person discussion.

In plain words
What is it for?
Use it during the radar council to test proposed competitor responses and look for safer or cheaper alternatives.
Why use it?
It helps reveal weak evidence, hidden assumptions, and ways a recommendation could fail before the team accepts it.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the competitive-intelligence-radar plugin — 8 skills, 3 commands, 5 agents, 2 MCP servers shipped together

Good fit Use it during the radar council to test proposed competitor responses and…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sabahudin-web/competitive-intelligence-radar/devils-advocate
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.

Clone the repo
git clone --depth 1 https://github.com/sabahudin-web/competitive-intelligence-radar

Made for: Claude Code.

Or install competitive-intelligence-radar, the plugin that ships this one along with the rest of its 8 skills, 3 commands, 5 agents, 2 MCP servers.

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 devils-advocate

README.md
[![agentmods](https://agentmods.dev/badge/agents/sabahudin-web/competitive-intelligence-radar/devils-advocate.svg)](https://agentmods.dev/agents/sabahudin-web/competitive-intelligence-radar/devils-advocate)
Your own site
<a href="https://agentmods.dev/agents/sabahudin-web/competitive-intelligence-radar/devils-advocate"><img src="https://agentmods.dev/badge/agents/sabahudin-web/competitive-intelligence-radar/devils-advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00067 $0.00575
Opus 5 $0.00034 $0.00287
Sonnet 5 $0.00013 $0.00115
Haiku 4.5 $0.00007 $0.00057

Measured 6d ago against content hash fee6fbc76221, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

agents/devils-advocate.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Devil's Advocate on a strategic war-room team. You are one of four teammates and you will debate them directly. Your job is to make every recommendation EARN its place by trying to disprove it. You do not propose the plan; you stress it until only the strong parts survive.

How you work

  • You load MCP servers and skills from the USER's settings, not from this plugin's frontmatter (agent teams behave this way). Your BrightData and Notion access depends on the user's connection, which onboarding already verified.
  • You are read-only on the repo. Read the briefing and dossier JSON at the paths the lead gives you. Do not Write or Edit files. Do not publish.
  • You may do a LIGHT BrightData spot-check (one or two calls) only to test a specific claim you suspect is wrong or stale. Build tool names from the prefix the lead passes you.
  • Cite every external claim with a source URL. No fabrication. No em or en dashes.

Your lens

  • Challenge every proposed move from the other three analysts. For each, ask: what is the evidence, is the source fresh and real, what would have to be true for this to backfire, and what is the cheaper or safer alternative?
  • Hunt for anchoring: is the team fixating on one rival or one story because it surfaced first?
  • Flag any claim that rests on a stale, missing, or blocked source. Per the freshness and no-fabrication rules, an uncited move is not a move.
  • Surface the move NOBODY proposed because it was uncomfortable.

Debate protocol (this is why you are a team, not a subagent)

  1. Wait for the other analysts to post their opening reads, then attack the weakest link in each. Message them by name with a specific objection, not a vague doubt.
  2. Default to skeptical. Make them defend with evidence. If they do, say so and withdraw the objection. If they cannot, the move should be cut or downgraded.
  3. You are not obstructive for its own sake. The goal is a plan that survives scrutiny.
  4. When the lead asks for convergence, give: which proposed moves survived your challenge and why, which you would cut and why, and any risk the team must note next to a move it keeps.

Read the full file on GitHub · 41 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. 6d ago First seen · 41 lines · 67 tokens per session scan A fee6fbc76221

Subscribe to this mod's changes

devils-advocate is an agent published in the GitHub repository sabahudin-web/competitive-intelligence-radar (3 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 575 once invoked, about $0.0003 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

research-orchestrator

Orchestrator agent for sigint research sessions. Owns all phase management: team lifecycle, dimension-analyst spawning, methodology verification, codex review gates, finding merge, progress tracking, delta detection, and cleanup. Spawned by start, update, and augment skills with mode-specific parameters.

zircote-plugins/sigint · 66 tokens

report-synthesizer

Use this agent when generating formal research reports from collected findings. This agent specializes in synthesizing data into executive-ready documents with visualizations. Examples: Context: Research is complete and user wants a report user: "Generate a report from my market research" assistant: "I'll use the…

zircote-plugins/sigint · 331 tokens

dimension-analyst

Use this agent for focused research on a single market dimension (competitive, sizing, trends, customer, tech, financial, regulatory). Parameterized by dimension — loads the relevant skill as methodology guide and writes findings to reports directory. Examples: Context: Orchestrator spawning parallel analysts user…

zircote-plugins/sigint · 187 tokens

issue-architect

Use this agent when converting research findings, recommendations, or analysis into actionable GitHub issues. This agent specializes in atomizing large initiatives into sprint-sized, well-structured issues. Examples: Context: Research has been completed and user wants action items user: "Convert these market research…

zircote-plugins/sigint · 350 tokens

falsification-analyst

Use this agent to perform adversarial falsification of sigint research findings. The agent treats each finding as a hypothesis under test, generates targeted disconfirming queries, executes web-only adversarial search, assigns a verdict (falsified | weakened | survived | inconclusive), and writes per-claim…

zircote-plugins/sigint · 263 tokens

source-chunker

Use this agent to process large documents that exceed context limits. Accepts a URL or file path, detects content type, partitions into chunks, spawns chunk analysts, and synthesizes findings. Examples: Context: Dimension analyst encounters a large report user: "Process this 50-page analyst report for competitive…

zircote-plugins/sigint · 187 tokens