Borrowing it
Nothing to install: this file belongs to thangnguyenworkspace/industry-pulse. 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/thangnguyenworkspace/industry-pulse/main/AGENTS.mdgit clone --depth 1 https://github.com/thangnguyenworkspace/industry-pulseWrote 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/thangnguyenworkspace/industry-pulse/agents-md)<a href="https://agentmods.dev/instructions/thangnguyenworkspace/industry-pulse/agents-md"><img src="https://agentmods.dev/badge/instructions/thangnguyenworkspace/industry-pulse/agents-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/thangnguyenworkspace/industry-pulse/agents-md"><img src="https://agentmods.dev/badge/instructions/thangnguyenworkspace/industry-pulse/agents-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 | $0.01521 | $0.01521 |
| Opus 5 | $0.00760 | $0.00760 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
industry-pulse AGENTS.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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for an agent operating or ingesting this repository. This is the single canonical agent-instruction file; CLAUDE.md imports it, so the two cannot drift. Edit this file, never CLAUDE.md. The human entry point is README.md.
What this is
industry-pulse is a watchlist-driven intelligence pipeline you run on demand. It crawls LinkedIn, X, RSS, and email, classifies and domain-tags every post in parallel against a profile you define, and writes one neutral, cited signals brief per run. The brief names nothing personal, so it stays forwardable; the relevance-and-delivery layer that scores a brief against your own context attaches at a documented seam and is not part of this repo. It is a frozen snapshot: the agent's job here is orientation, not modification.
Architecture
Three layers kept apart so the heavy reading never lands in the thread doing synthesis: pure-primitive crawl leaves, a parallel classify-and-tag fan-out, and a single-threaded synthesis pass that writes the brief. The full design, including the volume-aware auto-scaler and the context-isolation discipline, is the canonical statement in docs/architecture.md.
How to navigate
| Path | What it is | Read it when |
|---|---|---|
README.md |
Human entry point: thesis, quickstart, design decisions | Orienting to what the project is and how to run it |
docs/architecture.md |
The three layers, the auto-scaler, cost discipline, context isolation | You need the full mechanics behind a run |
.claude/skills/run-pulse/SKILL.md |
The orchestrator, top-to-bottom with every path and decision spelled out | Tracing or changing how a run is sequenced |
.claude/skills/research-crawl-*/SKILL.md |
The four crawl leaves (LinkedIn, X, RSS, email), one pure primitive each | Working on a single source lane |
config/ |
The lens you supply: profile.example.md + watchlists/*.example.md |
Setting up or changing what the pipeline reads through |
schemas/ |
Markdown contracts for every file the pipeline reads or writes | Checking or changing a file's shape |
docs/setup.md |
Clean-clone-to-first-brief setup, MCP servers included | Onboarding a fresh clone |
docs/extending.md |
The relevance seam, delivery adapters, adding a source lane | Building your own relevance or delivery layer |
scripts/rss-ingest.py |
The one standalone executable: the feedparser engine the RSS leaf calls | Running or debugging the RSS lane outside the harness |
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.
- 8d ago First seen · 81 lines · 1,521 tokens per session scan A fde4a540c72f
industry-pulse AGENTS.md is an instructions file published in the GitHub repository thangnguyenworkspace/industry-pulse (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,521 tokens to every session, about $0.0076 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.
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.
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).
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).
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.
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.