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/smyhlin/simklexpogter/agents-mdgit clone --depth 1 https://github.com/smyhlin/SimklExpoGterWrote 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/smyhlin/simklexpogter/agents-md)<a href="https://agentmods.dev/instructions/smyhlin/simklexpogter/agents-md"><img src="https://agentmods.dev/badge/instructions/smyhlin/simklexpogter/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 | $0.01317 | $0.01317 |
| Opus 5 | $0.00659 | $0.00659 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
SimklExpoGter 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository instructions for AI coding agents and human maintainers.
Project summary
SimklExpoGter is a Go/Wails/Svelte desktop + CLI + TUI app for exporting and backing up Simkl data.
Supported modes:
- Wails desktop GUI
- headless CLI
- dependency-free terminal UI
- Windows Task Scheduler recurring backups
- Linux systemd user timer recurring backups
The project is intentionally cross-platform. Do not reintroduce Windows-only assumptions.
Ground rules
- Keep GUI, CLI and TUI behavior backed by the same service layer.
- Keep TUI dependency-free unless there is a strong reason to change that.
- Keep Linux scheduling based on systemd user timers.
- Keep Windows scheduling based on Task Scheduler.
- Keep CLI/TUI Simkl auth on PIN login by default.
- Do not use OAuth redirect URI login for CLI/TUI unless explicitly working on registered-redirect web/GUI behavior.
- Do not commit generated local build outputs.
- Do not commit secrets, tokens, local settings, or exported user backups.
- Prefer small, testable service-layer changes over UI-only fixes.
Build commands
Linux:
./scripts/bootstrap.sh
./build.sh check
./build.sh linux
./build.sh linux-cli
Windows:
scripts\bootstrap.bat
build.bat check
build.bat windows
build.bat windows-cli
PowerShell:
.\scripts\bootstrap.ps1
.\build.ps1 windows
Validation checklist
Before committing, run what is available on your platform:
./build.sh check
./build.sh linux
./build.sh linux-cli
For Linux scheduler changes, also run:
./build/bin/SimklExpoGter schedule enable --frequency daily --time 02:00 --max-backup-age 24h --format both --field-mode all --content shows,movies,anime
systemctl --user status SimklExpoGterRecurringBackup.timer --no-pager --full
systemctl --user list-timers '*SimklExpoGter*'
For CLI/TUI auth changes, verify the PIN flow:
./build/bin/SimklExpoGter auth login
./build/bin/SimklExpoGter auth status
./build/bin/SimklExpoGter tui
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 · 182 lines · 1,317 tokens per session scan A 0cb945b4dd81
SimklExpoGter AGENTS.md is an instructions file published in the GitHub repository smyhlin/SimklExpoGter (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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
swift-tui AGENTS.md
AGENTS.md instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.
swift-tui CLAUDE.md
Claude Code instructions for SwiftTUI/swift-tui, a project described as: SwiftUI semantics, drawn in terminal cells — macOS/Linux/Windows/WASI.
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.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.