competitive-intelligence-radar: Instructions file for Claude Code

CLAUDE.md

competitive-intelligence-radar CLAUDE.md is an instructions file for Claude Code from sabahudin-web/competitive-intelligence-radar. It costs 1,247 tokens per session, scanned A, original, MIT.

Instructions for a Claude Code plugin that tracks competitors through weekly web research and produces strategic reports. It uses Bright Data for live web data, parallel scouting agents, and an analyst team for deeper discussion.

In plain words
What is it for?
Use them to set up competitor tracking, gather updates from multiple competitors, compare results with earlier runs, and publish briefing or strategy reports.
Why use it?
They define how the plugin should be configured and how its setup, weekly radar, and strategic council workflows should operate in a fresh project.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is sabahudin-web/competitive-intelligence-radar's own configuration. It tells Claude Code how to work on competitive-intelligence-radar 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 competitive-intelligence-radar configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to sabahudin-web/competitive-intelligence-radar. 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/sabahudin-web/competitive-intelligence-radar/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sabahudin-web/competitive-intelligence-radar

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 competitive-intelligence-radar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sabahudin-web/competitive-intelligence-radar/claude-md/github.svg)](https://agentmods.dev/instructions/sabahudin-web/competitive-intelligence-radar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sabahudin-web/competitive-intelligence-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/sabahudin-web/competitive-intelligence-radar/claude-md/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 competitive-intelligence-radar CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sabahudin-web/competitive-intelligence-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/sabahudin-web/competitive-intelligence-radar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,247 This file is loaded in full into every session.
When invoked 1,247 The same file — it is already loaded in full.
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 $0.01247 $0.01247
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured 9d ago against content hash 07b513a54d92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

competitive-intelligence-radar CLAUDE.md 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 9d 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.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in the Competitive Intelligence Radar plugin repository.

What this project is

A Claude Code plugin that runs a weekly competitor radar for business owners and convenes a strategic war room on demand. It showcases the BrightData MCP for live web data and deliberately uses BOTH Claude Code parallelism primitives, each where it honestly fits.

  • /radar-setup onboards: asks about and live-tests the user's BrightData and Notion connection, shows the proposed Notion schema for approval, checks agent-team prerequisites.
  • /radar is the weekly GATHER: it fans out one competitor-scout SUBAGENT per competitor in parallel; each gathers a cited dossier and reports back; the orchestrator diffs vs last run, merges one briefing, and publishes to three surfaces.
  • /radar-council is the on-demand ANALYZE: it spins up a real experimental AGENT TEAM of four analyst teammates who message and challenge each other, then publishes a Strategic War Room addendum.

First thing to do in a fresh checkout

If the user has just installed or cloned this, point them to /radar-setup. Nothing else runs until radar.config.json exists with verified MCP prefixes.

Architecture you must respect

  • GATHER uses SUBAGENTS. Scouts are independent and only report back; they never message each other. Do not turn the gather into an agent team.
  • DEBATE uses an AGENT TEAM. Analysts must see and challenge each other, which only a team allows. Do not turn the debate into plain subagents.
  • The full rationale is in rules/subagents-vs-agent-teams.md. Read it before changing either flow.

Hard rules (these are not optional)

These live in rules/. Every generated artifact must obey them:

  1. no-fabrication.md: every factual claim carries a real source_url fetched this run plus fetched_at. No value without a source. Model knowledge is never a source.
  2. freshness.md: every field has a recency window and a fetched_at; stale data is labeled, not presented as current.
  3. cost-control.md: prefer *_batch BrightData tools; cap competitors at 8; lean scout depth by default; the council is token heavy.
  4. automation-levels.md: AUTONOMOUS by default; CHECKPOINT for Notion database creation, for the MCP connection check at onboarding, for /radar-council, and for any GitHub push.
  5. no-em-dashes.md: never use the em dash (U+2014) or en dash (U+2013) anywhere, including in this file. Use commas, colons, or hyphens.

Read the full file on GitHub · 95 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. 9d ago First seen · 95 lines · 1,247 tokens per session scan A 07b513a54d92

Subscribe to this mod's changes

competitive-intelligence-radar CLAUDE.md is an instructions file published in the GitHub repository sabahudin-web/competitive-intelligence-radar (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,247 tokens to every session, about $0.0062 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens