Borrowing it
Nothing to install: this file belongs to nsyll/clawdometer-eink. 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/nsyll/clawdometer-eink/main/AGENTS.mdgit clone --depth 1 https://github.com/nsyll/clawdometer-einkWrote 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/nsyll/clawdometer-eink/agents-md)<a href="https://agentmods.dev/instructions/nsyll/clawdometer-eink/agents-md"><img src="https://agentmods.dev/badge/instructions/nsyll/clawdometer-eink/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/nsyll/clawdometer-eink/agents-md"><img src="https://agentmods.dev/badge/instructions/nsyll/clawdometer-eink/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 | $0.01173 | $0.01173 |
| Opus 5.5 | $0.00469 | $0.00469 |
| Sonnet 5.5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
clawdometer-eink 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clawdometer-eink CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clawdometer — guide for AI coding agents
Read this before touching code. It encodes the hard-won gotchas; violating them produces firmware that compiles fine and then fails silently on the desk.
What this is
An ESP32-S3 e-paper gadget showing Claude usage + Claude Code live status. Three parts:
firmware/ (PlatformIO, Arduino, C++) · daemon/ (single-file Python, bleak+httpx, macOS-first) · hooks/ (Claude Code hook, stdlib-only Python). Interfaces between them are specced in docs/PROTOCOL.md; component responsibilities in docs/ARCHITECTURE.md.
Build / run / test
# firmware
cd firmware && pio run # compile (always do this before claiming success)
./flash.sh # upload over USB — auto-picks the real serial port
pio device monitor # 115200 baud serial logs
# daemon (needs a real macOS Terminal for Bluetooth permission)
cd daemon && python3 -m venv .venv && ./.venv/bin/pip install -r requirements.txt
./.venv/bin/python claude_usage_daemon.py # live dashboard
./.venv/bin/python claude_usage_daemon.py --plain # line logs
# hook (test standalone; must ALWAYS exit 0)
echo '{"hook_event_name":"Stop","transcript_path":"<some.jsonl>"}' | python3 hooks/cc_status_hook.py
cat ~/.clawd/cc_status.json
There is no automated test suite. Verify firmware changes by compiling; verify daemon logic by importing the module and calling functions directly (it's import-safe); verify the hook with synthetic stdin payloads as above.
Hardware gotchas (the expensive lessons)
EPD_PWR(GPIO6) is ACTIVE-LOW.LOW= panel powered. Get this backwards and the screen is just blank with no error.- ES8311 codec needs MCLK before I2C. I2S must be started before
es8311_init, or the codec never ACKs. I2S clocks are stopped between chimes for power —playMelodyrestarts them. - SPI pins must be remapped after
display.init()(seeDisplay.cpp); the reverse order breaks the panel on this board. - Deep sleep releases GPIO pads.
VBAT_HOLD(GPIO17) keeps the battery latch closed — it MUST begpio_hold_en'd beforeesp_deep_sleep_start()or the board powers itself off and won't wake. Same technique holds the panel/audio rails off. - BLE payload > default MTU. The JSON is ~450 B; the device sets MTU 512. If you grow the payload past ~500 B, writes fail silently — shrink field names or split.
- NimBLE-Arduino must stay 1.4.x while the platform is Arduino-ESP32 2.0.x (PlatformIO
espressif32). 2.x NimBLE needs a newer core.
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.
- 2mo ago First seen · 61 lines · 1,173 tokens per session scan A c09e95ef229e
clawdometer-eink AGENTS.md is an instructions file published in the GitHub repository nsyll/clawdometer-eink (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0047 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.