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/luzivog/toks/agents-mdgit clone --depth 1 https://github.com/Luzivog/toksWrote 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/luzivog/toks/agents-md)<a href="https://agentmods.dev/instructions/luzivog/toks/agents-md"><img src="https://agentmods.dev/badge/instructions/luzivog/toks/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 | $0.00968 | $0.00968 |
| Opus 5 | $0.00484 | $0.00484 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
toks 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 3d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Toks is a Rust workspace. crates/toks/ is the GPUI app,
crates/toks-core/ owns account, limit, and history behavior, and
crates/toks-ingest/ contains repository-owned parsing, caching, and
pricing. Tests live beside modules or under each crate's tests/; desktop
assets are in assets/, and repository checks are in scripts/quality/.
Build, Test, and Development Commands
cargo run -p toks --lockedstarts the Linux desktop app.cargo run -p toks-core --bin toks-dump --locked -- historyprints a headless snapshot; uselimitsfor account limits.cargo check --locked -p toksis the default UI compile check.cargo test --locked -p toks --lib <filter>runs focused unit tests.cargo test --locked -p toks --test <target> <filter>runs one integration target with only required features.cargo clippy --locked -p toks --lib -- -D warningslints the app.cargo fmt --all --checkverifies formatting.scripts/quality/check-repository.shchecks source-size, import, and portability rules.
Run workspace tests and Clippy once as final gates, not after each edit. Build
release only for release, installation, or packaging. Before broad/all-target or
release-LTO commands, check free disk and active Cargo, rustc, and linker work;
wait instead of competing or writing into unsafe free space. Keep Cargo's native
parallelism and iterative incremental compilation. Use CARGO_INCREMENTAL=0
only for a coordinated one-shot gate, and --profile debugging only for full
debug symbols. Without explicit approval, do not clean/delete target artifacts,
change a shared target directory, or add build caches/linkers. Never add
machine-specific linker paths or home directories.
Coding Style & Naming Conventions
Use rustfmt and Rust naming: snake_case items, CamelCase types,
and SCREAMING_SNAKE_CASE constants. Prefer typed structs and enums at crate
seams. Keep hand-written production files below 200 lines and tests below 500;
split by responsibility. Avoid internal wildcard imports/re-exports. Generated
exceptions require a generated path/name and marker. Existing ingest debt is
ratcheted: entries may shrink, never grow.
Use Rust 2018 module roots: foo.rs with an optional foo/ directory; do not
add mod.rs files. Put a module's tests in sibling foo_tests.rs, or use
foo/tests.rs plus foo/tests/*.rs for multi-file suites; do not define inline
test modules in production files.
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.
- 3d ago First seen · 83 lines · 968 tokens per session scan A 49cf6df7581d
toks AGENTS.md is an instructions file published in the GitHub repository Luzivog/toks (2 stars, last pushed 4d ago), licensed MIT. It adds 968 tokens to every session, about $0.0048 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
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
hex AGENTS.md
AGENTS.md instructions for anomalyco/hex, covering hex agent guide, purpose, feature map, architecture and invariants.
lite AGENTS.md
AGENTS.md instructions for ultralytics/lite, covering agents.md, core principles (critical), pr workflow, commands and architecture.
lite CLAUDE.md
Claude Code instructions for ultralytics/lite, a project described as: A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.
operance AGENTS.md
Instructions for raunakkathuria/operance, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and architecture guardrails.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.