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/arfct/chronology-watchface/agents-mdgit clone --depth 1 https://github.com/arfct/chronology-watchfaceWrote 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/arfct/chronology-watchface/agents-md)<a href="https://agentmods.dev/instructions/arfct/chronology-watchface/agents-md"><img src="https://agentmods.dev/badge/instructions/arfct/chronology-watchface/agents-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 | $0.02543 | $0.02543 |
| Opus 5 | $0.01272 | $0.01272 |
| Sonnet 5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
chronology-watchface 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 4d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chronology
A watchface with an analog dial whose rim sweeps through the screen at the current hour, configurable colors, and two dial styles (classic and large numerals). Two implementations share this repo:
pebble/— original Pebble version (C + Clay JS config)wear/— Wear OS version (Kotlin, androidx.wear.watchface)
Pebble (pebble/)
Run all Pebble commands from the pebble/ directory.
| Task | Command |
|---|---|
| Build | pebble build |
| Run on gabbro emulator | pebble build && pebble install --emulator gabbro && pebble logs |
| Screenshot all emulators | npm run screenshots |
| Install on phone | npm run install-phone |
Emulators
Target platforms: aplite, basalt, chalk, diorite, emery, gabbro
To run a specific emulator:
pebble install --emulator <platform>
pebble logs --emulator <platform>
pebble screenshot <output.png> --emulator <platform>
If an emulator gets stuck at boot, wipe its flash:
pkill -9 -f <platform>
rm ~/Library/Application\ Support/Pebble\ SDK/4.9.169/<platform>/qemu_spi_flash.bin
Configuration
Settings are sent from the phone JS layer to the watch via Pebble.sendAppMessage. Persisted on the watch at these keys:
| Key | Message key | Persist key | Description |
|---|---|---|---|
BG_HEX |
10000 | 5 | Background color |
FACE_HEX |
10001 | 6 | Face color |
HAND_HEX |
10002 | 7 | Hand color |
FACE_CLEAR |
10003 | 8 | Transparent face toggle |
DIAL_STYLE |
10004 | 9 | 0 = classic, 1 = large numerals |
To send a setting to a running emulator:
pebble send-app-message --emulator <platform> --int <message_key>=<value>
Send each key as its own message. Passing multiple --int flags in a single
send-app-message call only delivers one of them (the others are silently
dropped). To change several settings, issue one command per key.
Example — enable large numerals on all emulators:
for platform in aplite basalt chalk diorite emery gabbro; do
pebble send-app-message --emulator $platform --int 10004=1
done
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.
- 4d ago First seen · 216 lines · 2,543 tokens per session scan A 39864ae8f8cf
chronology-watchface AGENTS.md is an instructions file published in the GitHub repository arfct/chronology-watchface (10 stars, last pushed 11d ago), licensed MIT. It adds 2,543 tokens to every session, about $0.0127 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
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
phone-mcp CLAUDE.md
Instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.