What is DailyBrief AGENTS.md?

Repository instructions for DailyBrief, a local program that gathers news feeds, adds language-model analysis, and produces one HTML report. They describe the project layout, rules, and common commands for coding agents.

They help with source fetchers, report rendering, trading data, scripts, and other DailyBrief development tasks.

They give an agent the project context it needs, so it does not have to guess how the repository works or how it should be changed.

DailyBrief AGENTS.md — Instructions file by leiting-eric

Install

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.

agentmods

npx agentmods add instructions/leiting-eric/dailybrief/agents-md

Clone the repo

git clone --depth 1 https://github.com/leiting-eric/DailyBrief

Made for: Codex, OpenCode.

Per session 1,637 This file is loaded in full into every session.

When invoked 1,637 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

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	$0.01637	$0.01637
Opus 5	$0.00818	$0.00818
Sonnet 5	$0.00327	$0.00327
Haiku 4.5	$0.00164	$0.00164

Measured 3d ago against content hash 59d487268cf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DailyBrief AGENTS.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Don't add Playwright / Puppeteer for fetching — the project stays light with curl + JSON APIs

AGENTS.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operational knowledge for any AI coding agent working on this repo (Claude Code, Codex, Cursor, Continue.dev, Aider, etc.). Claude Code users get a richer SKILL.md auto-loaded; this file is the universal subset everyone reads.

What this project is

daily-brief is a local-first pipeline that fetches 23 RSS / API news sources daily (22 in en mode after locale filtering), runs LLM enrichment, and renders a single self-contained HTML report. It runs on the user's machine via the OS scheduler, OR in GitHub Actions publishing to GitHub Pages. No web framework, no DB, no servers.

The repo's CLAUDE.md includes this file via @AGENTS.md. Don't add stack-specific lore (Next.js, etc.) — there's none in this codebase.

Project layout (essentials)

lib/
  ai/           # LLM dispatcher + 5 backend implementations + prompts
  sources/      # fetcher dispatch + per-source TS modules
  trading/      # Yahoo finance + technical indicators + watchlist
  output/       # render.ts (HTML+MD generation), all CSS inlined
  utils.ts      # tiny shared helpers (todayKey, getReportTz)
scripts/
  _env.ts             # dotenv preload — imported FIRST by every entry script
  daily.ts            # main pipeline (5-8 min, ~6 LLM calls)
  dry-run.ts          # fetch-only validation (~30s, no LLM)
  render.ts           # re-render HTML/MD from cached sidecar (~1s)
  regen-trading.ts    # rerun just the trading commentary
  regen-enrich.ts     # top up missing summaries for a subgroup
  build-site.mjs      # generate index.html + archive.html for static hosting
  deploy.mjs          # scp HTML to a remote nginx host (opt-in)
  sources.ts          # `npm run sources` — list/validate sources.config.json
  install.mjs         # cross-platform OS scheduler registration
  run-daily.mjs       # scheduler wrapper (daily + log + deploy + open)
  open-report.mjs     # cross-platform "open latest report" helper
  uninstall.mjs       # tear down scheduler + ~/.claude/ links
  quota-report.ts     # LLM call usage summary
sources.config.json   # SINGLE SOURCE OF TRUTH for the source registry

Read the full file on GitHub · 101 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.

3d ago First seen · 101 lines · 1,637 tokens per session scan A 59d487268cf3

Subscribe to this mod's changes

DailyBrief AGENTS.md is an instructions file published in the GitHub repository leiting-eric/DailyBrief (338 stars, last pushed 4d ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM ai claude-code claude-skills daily-digest news-aggregator

DailyBrief AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

AGENTS.md

What this project is

Project layout (essentials)

What this file has done since we first saw it

Other instructions, from other repositories

FreshRSS php.instructions.md

FreshRSS _general.instructions.md

FreshRSS css.instructions.md

FreshRSS markdown.instructions.md

FreshRSS i18n.instructions.md

FreshRSS javascript.instructions.md