What is compete CLAUDE.md?

A Claude Code skill that turns a software repository into a competitive-intelligence report. Competitive intelligence means researching a product and its competitors to compare their capabilities and market position.

Use it to extract product information, discover competitors, validate structured JSON results, and generate a self-contained HTML report.

It gives the research process a defined pipeline for analysing a repository, planning web research, normalising findings, and producing a browser-viewable report.

How lbj96347/compete configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lbj96347/compete. 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/lbj96347/compete/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lbj96347/compete

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lbj96347/compete/claude-md/github.svg)](https://agentmods.dev/instructions/lbj96347/compete/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lbj96347/compete/claude-md"><img src="https://agentmods.dev/badge/instructions/lbj96347/compete/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lbj96347/compete/claude-md"><img src="https://agentmods.dev/badge/instructions/lbj96347/compete/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,470 This file is loaded in full into every session.

When invoked 1,470 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.

Model	Per session	Once invoked
Fable 5.1	$0.01470	$0.01470
Opus 5.5	$0.00588	$0.00588
Sonnet 5.5	$0.00294	$0.00294
Haiku 4.5	$0.00147	$0.00147

Measured 2mo ago against content hash 1b2d1812d553, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compete 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 2mo 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

compete is itself a Claude Code Skill (skills/compete/SKILL.md at the root), not a conventional app. It turns the repository Claude is invoked in into a competitive intelligence report. The deliverables are: Python helper scripts (stdlib only), JSON Schemas, reference docs, and a self-contained HTML report template. There is no package manager, build system, or test framework — just python and a browser.

When the skill runs, Claude itself is part of the pipeline: the scripts emit research plans, Claude executes them with WebSearch/WebFetch, and the scripts normalize Claude's findings back into schema-valid JSON.

Commands

Requirements: Python 3.9+ (stdlib only; jsonschema/referencing optional — scripts fall back to built-in structural checks when absent).

The pipeline runs in five stages. The two middle stages are two-phase (plan → Claude does web research → build):

# 1. Product Intelligence — repo → product.json
python skills/compete/scripts/analyze_repo.py --repo . --validate

# 2. Competitor Discovery (two-phase)
python skills/compete/scripts/discover_competitors.py plan  --product product.json        # → research plan (stdout)
#   ...Claude runs the plan with WebSearch/WebFetch → candidates.json...
python skills/compete/scripts/discover_competitors.py build --product product.json \
  --candidates candidates.json --validate                                  # → competitors.json

# 3. Intelligence Collection (two-phase)
python skills/compete/scripts/collect_intelligence.py plan  --competitors competitors.json
#   ...Claude runs the plan → findings.json...
python skills/compete/scripts/collect_intelligence.py build --competitors competitors.json \
  --findings findings.json --validate                                      # → companies/pricing/techstack/social/marketing/seo.json

# 4 + 5. Knowledge Graph + Report — all datasets → report.json + report.html
python skills/compete/scripts/build_report.py --input-dir . --output-dir ./insightkit-output --open

Read the full file on GitHub · 106 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.

2mo ago First seen · 106 lines · 1,470 tokens per session scan A 1b2d1812d553

Subscribe to this mod's changes

compete CLAUDE.md is an instructions file published in the GitHub repository lbj96347/compete (9 stars, last pushed 4mo ago), licensed MIT. It adds 1,470 tokens to every session, about $0.0059 per session on Opus 5.5. 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.

Marketing and SEO Research

compete CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
compete CLAUDE.mdlbj96347/compete	Instructions file	9	4mo ago	MIT	A	1,470	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

compete: Instructions file for Claude Code