router-daybook: Instructions file for Codex

AGENTS.md

router-daybook AGENTS.md is an instructions file for Codex, OpenCode from jameslbarnes/router-daybook. It costs 2,410 tokens per session, scanned A, original, MIT.

Repository instructions for Teleport Router’s Electron desktop interface, which reads local Claude Code and Codex sessions and can create approved daily reflections for a shared feed.

In plain words
What is it for?
Use them when modifying session reading, reflection generation, approval and posting, the Electron interface, or its build and test process.
Why use it?
They explain the data flow, privacy constraints, product naming, and Electron limitations so changes do not break the intended review-before-posting behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is jameslbarnes/router-daybook's own configuration. It tells Codex and OpenCode how to work on router-daybook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything router-daybook configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jameslbarnes/router-daybook. 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/jameslbarnes/router-daybook/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jameslbarnes/router-daybook

Made for: Codex, OpenCode.

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.

agentmods badge for router-daybook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jameslbarnes/router-daybook/agents-md.svg)](https://agentmods.dev/instructions/jameslbarnes/router-daybook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jameslbarnes/router-daybook/agents-md"><img src="https://agentmods.dev/badge/instructions/jameslbarnes/router-daybook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,410 This file is loaded in full into every session.
When invoked 2,410 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02410 $0.02410
Opus 5 $0.01205 $0.01205
Sonnet 5 $0.00482 $0.00482
Haiku 4.5 $0.00241 $0.00241

Measured 6d ago against content hash 7da14f7ba77f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

router-daybook 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 6d 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.

AGENTS.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working notes for agents on Teleport Router (repo: router-daybook)

Guidance for AI agents (and humans) working in this repo. Read this before making changes; it records why things are the way they are so you don't undo deliberate decisions. See README.md for the user-facing tour.

It is not a standalone product — it's the desktop interface to the Router, and ultimately the front end for router-teamwork. "Daybook" is just the repo codename; the product is Teleport Router.

What this is

Teleport Router (Electron desktop app; package name router, repo router-daybook) reads your local Claude Code (~/.claude/projects/*/*.jsonl) and Codex (~/.codex/sessions/...) sessions, writes a first-person daily reflection via the local claude -p CLI, and — only when you approve — posts it to the Router, a cohort's shared read-only feed (https://router.teleport.computer, override ROUTER_SERVER).

Founding values, in priority order: simple, calm, privacy-conscious — and a fourth that emerged: restraint (the generator says nothing fake; see the eval). When in doubt, choose the simpler, quieter, more honest option.

How it works (the pipeline)

collectgeneratereview/refinepost:

  1. transcripts.js discovers sessions since your last Router post (collectSinceLastPost, anchored to router.lastOwnPostMs — the server timestamp — with a 7-day floor), scope-gates them deny-by-default before reading bodies, and compacts them into a digest. Secrets are masked here, before the digest can become a prompt.
  2. reflect.js spawns claude -p (the user's subscription) to write the post plus a bundled firstQuestion (the refine opener). Its prompt is built FROM postspec.js so the generator and the eval share one contract. Scrubs the digest before the spawn and the post after.
  3. renderer shows the draft AS a directly-editable <textarea> (no markdown render, no read-only view). Under it: the bundled question + a "Refine in interview" CTA that opens the interview seeded on that question. Footer: Start over · Skip · Post.
  4. router.post re-scrubs the exact outgoing bytes and posts to /api/entries (staged, deletable). The header posting streak (router.postStreak) refreshes.

Read the full file on GitHub · 143 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.

  1. 6d ago First seen · 143 lines · 2,410 tokens per session scan A 7da14f7ba77f

Subscribe to this mod's changes

router-daybook AGENTS.md is an instructions file published in the GitHub repository jameslbarnes/router-daybook (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,410 tokens to every session, about $0.0120 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens