Borrowing it
Nothing to install: this file belongs to tig/esprec. 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/tig/esprec/main/AGENTS.mdgit clone --depth 1 https://github.com/tig/esprecWrote 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/tig/esprec/agents-md)<a href="https://agentmods.dev/instructions/tig/esprec/agents-md"><img src="https://agentmods.dev/badge/instructions/tig/esprec/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/tig/esprec/agents-md"><img src="https://agentmods.dev/badge/instructions/tig/esprec/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 | $0.05384 | $0.05384 |
| Opus 5.5 | $0.02154 | $0.02154 |
| Sonnet 5.5 | $0.01077 | $0.01077 |
| Haiku 4.5 | $0.00538 | $0.00538 |
Grade A, and why
esprec 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.
How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how to use esprec
Canonical playbook for AI coding agents (Claude Code, Grok Build, Copilot, Codex, and kin) when the human says use tig/esprec or pastes a README Getting Started prompt.
Human overview: README.md. Product requirements: specs/spec.md. CI ladder: specs/ci.md. Short CLI dump: esprec agent-guide.
esprec is eyes, not hands. Capture device pixels over USB serial → host PNG/GIF. Product serial commands (btn, identity, deploy) stay in the product / Silico path. Do not invent a private capture stack when this tool covers the wire.
0. Load path (do this first)
| Priority | Open | When |
|---|---|---|
| 1 | This file (AGENTS.md) |
Any “use esprec” / screenshot / golden / mockup-vs-device task |
| 2 | esprec agent-guide |
Need flag surface only |
| 3 | specs/spec.md / specs/ci.md | Changing protocol, component, or CI shape |
| — | Product GCU AGENTS.md / Silico first-ship |
Deploy, identity, board COM — not capture wire format |
If you only skimmed the README examples, you have not followed this playbook.
1. Mission in one line
device UI → full-frame shadow → USB serial (ESPREC1 + base64) → host PNG and/or GIF
- On-device:
component/esprecemits frames; does not encode PNG/GIF. - Host: this package’s CLI/library receives frames and post-processes images.
- Integrity: ESPREC1 CRC covers metadata + raster. Truncation, wrong length, or header tamper fail closed — never silent “valid” junk images.
2. Install (host)
Python ≥ 3.11. Prefer a sibling clone next to the product GCU:
# layout: .../tig/esprec and .../tig/<gcu>
python -m pip install -e "../esprec[dev]" # from GCU repo
# or from this checkout:
python -m pip install -e ".[dev]"
esprec agent-guide
esprec snapshot --fake -o face.png # offline smoke (no board)
From git without a sibling tree:
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 · 466 lines · 5,384 tokens per session scan A 7c1548b212f6
esprec AGENTS.md is an instructions file published in the GitHub repository tig/esprec (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 5,384 tokens to every session, about $0.0215 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.
esprec AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| esprec AGENTS.mdtig/esprec | Instructions file | 5 | 3mo ago | Apache-2.0 | A | 5,384 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |