Borrowing it
Nothing to install: this file belongs to geekjourneyx/industry-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geekjourneyx/industry-research/main/CLAUDE.mdgit clone --depth 1 https://github.com/geekjourneyx/industry-researchWrote 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/instructions/geekjourneyx/industry-research/claude-md)<a href="https://agentmods.dev/instructions/geekjourneyx/industry-research/claude-md"><img src="https://agentmods.dev/badge/instructions/geekjourneyx/industry-research/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.
<a href="https://agentmods.dev/instructions/geekjourneyx/industry-research/claude-md"><img src="https://agentmods.dev/badge/instructions/geekjourneyx/industry-research/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01121 | $0.01121 |
| Opus 5 | $0.00561 | $0.00561 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
industry-research 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 84 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
A multi-agent adversarial industry research engine (Claude Code skill). Takes a fuzzy industry/sector/business-opportunity request, runs it through a structured "hypothesis → adversarial challenge → synthesis" pipeline, and outputs a research report with source citations and confidence scores. Has a specialized vertical for restaurant/retail/supply-chain research that uses operating-trace verification instead of narrative-based analysis.
Architecture
The engine is defined entirely in SKILL.md — it is the orchestrator that coordinates four sub-agents. There is no application code; the system runs as a Claude Code skill invoked via /industry-research.
Agent roles (all in agents/):
| Agent | File | Role |
|---|---|---|
| Engagement Manager | agents/engagement-manager.md |
Structures the research question into a ghost deck (analysis skeleton) and optional entity evidence plan |
| Blue Team | agents/blue-team.md |
Bull-case analyst — builds evidence-backed optimistic thesis |
| Red Team | agents/red-team.md |
Bear-case analyst — pre-mortem + adversarial challenge |
| Chief Arbitrator | agents/chief-arbitrator.md |
Hegelian synthesis — resolves red/blue conflict into a final report with verdicts |
Execution flow (stages in SKILL.md):
- Domain Grounding (Phase 1): Industry taxonomy mapping → web research → context dictionary → user confirmation
- Business Physics Modeling (Step 2.0, restaurant/retail/supply-chain only): Entity evidence plan (
entity_evidence_plan.json) - Ghost Deck (Step 2.1): MECE chapter structure with falsifiable action titles
- Round 1 (Step 2.2): Red and blue agents run in parallel — independent analysis
- Round 2 (Step 2.3): Cross-rebuttal — each side sees the other's R1 output (skipped in
briefmode unless conflicts are severe) - Arbitration (Step 2.4): Chief arbitrator produces
final_report.md+report_metadata.json - Validation (Step 2.5): Automated structure check via
scripts/validate_report.py
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.
- 12d ago First seen · 84 lines · 1,121 tokens per session scan A 748adccf1670
industry-research CLAUDE.md is an instructions file published in the GitHub repository geekjourneyx/industry-research (21 stars, last pushed 2mo ago), licensed MIT. It adds 1,121 tokens to every session, about $0.0056 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
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.
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).