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.
npx agentmods add instructions/architektapx/hackernews-brief/claude-mdgit clone --depth 1 https://github.com/ArchitektApx/HackerNews-BriefWrote 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/architektapx/hackernews-brief/claude-md)<a href="https://agentmods.dev/instructions/architektapx/hackernews-brief/claude-md"><img src="https://agentmods.dev/badge/instructions/architektapx/hackernews-brief/claude-md.svg" alt="Measured on agentmods" 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 | $0.01607 | $0.01607 |
| Opus 5 | $0.00804 | $0.00804 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
HackerNews-Brief 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 5d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repository.
What this is
A Claude Code plugin that produces a personalized daily Hacker News brief. The repo is both the
marketplace and the single plugin it serves, which is why marketplace.json points at "./".
Python standard library only, no dependencies, by design. The interest profile is local JSON. Nothing leaves the machine except requests to HN's public Algolia API and to article pages the user asked to have summarized.
Working in this repository
master is protected by a ruleset with no bypass, so nothing lands by pushing to it, including
from the owner. Branch, push the branch, open a PR, merge it yourself. A PR needs the verify
check green and squash as its merge method; it needs no approvals.
Every commit must be signed. Local commits inherit commit.gpgsign; an unsigned commit is
refused at push, not at review.
Repository policy requires every action in .github/workflows/ to be pinned to a full commit
SHA, version as a trailing comment. A tag reference does not fail review, it fails the run.
Dependabot owns those SHAs and bumps them in one grouped PR monthly, so bumping one by hand only
creates a conflict with the next one.
A workflow file registers with GitHub only when a push modifies it. One added in a repository's first push stays invisible until a later commit touches the file.
Gotchas
One Bash call is one bare hn-brief invocation. A permission rule is matched against each
statement of a compound command and saved carrying that statement's arguments, and at most five
rules are kept per approval. A preamble split into five statements therefore asks five times, and
a rule saved for shown <interest> never matches the next run's shown <other-interest>, so the
prompting never stops. bin/hn-brief and hn.py exist only so every phase is one fixed-shape
command that Bash(hn-brief *) covers for good. Two things quietly undo that: adding a second
statement to a documented call, and writing the interpreter or a path instead of the bare command,
which puts the installed version number into the saved rule so the next release starts asking
again.
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.
- 5d ago First seen · 125 lines · 1,607 tokens per session scan A 03c1d1e4d919
HackerNews-Brief CLAUDE.md is an instructions file published in the GitHub repository ArchitektApx/HackerNews-Brief (1 stars, last pushed 19d ago), licensed MIT. It adds 1,607 tokens to every session, about $0.0080 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
platform-skills copilot-instructions.md
Copilot instructions for nitinjain999/platform-skills, covering platform engineering instructions for github copilot, version: 1.40.0, source: https://github.com/nitinjain999/platform-skills, response contract and core principles.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
curie CLAUDE.md
Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
agentic-validation-skills CLAUDE.md
Claude Code instructions for vivekkrishna/agentic-validation-skills, covering agentic test automation guidelines (cige), 1. establish context before testing, 2. anchor every test to intent, 3. define guardrails before executing and 4. treat execution as adaptive guidance.